LeanrIQ
Server Details
Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 137 tools
There are extensive duplicate aliases (e.g. leanriq_build_ad / leanriq_build_agent_ad / build_ad all do the same thing) and genuinely overlapping build tools (build_ad, build_campaign_creative_set, build_creative_os, build_dooh, build_videoad). Identity/capability helpers also overlap (get_capabilities vs get_leanriq_capabilities, get_current_seat vs leanriq_current_seat), forcing an agent to reason about deprecation rather than intent.
The dominant pattern is consistent verb_noun snake_case. However the surface mixes prefixed and unprefixed conventions (leanriq_*, leanr_*, bare names), so identical operations appear under multiple naming forms, which undercuts predictability.
137 tools is extreme for any single server; even discounting the large block of deprecated aliases, roughly 70 live tools remain. The deprecated duplicates bloat the registry without adding capability, making the set hard to navigate.
The domain (adtech creative production: advertisers, campaigns, creatives, flights, trafficking, QA, intelligence, feedback) is covered quite thoroughly with lifecycle operations across resources. Coverage is a strong point even though the surface is over-stuffed.
Available Tools
137 toolsarchive_advertiserarchive advertiserCDestructiveIdempotentInspect
archive advertiser. Classification: writes to Studio, destructive. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), advertiserId (required), dryRun, seatId, +20 more. Returns: data, meta, error, status, +1 more
archive_campaignarchive campaignBDestructiveIdempotentInspect
archive campaign. Classification: writes to Studio, destructive. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), campaignId (required), dryRun, seatId, +20 more. Returns: data, meta, error, status, +1 more
archive_creativearchive creativeBDestructiveIdempotentInspect
archive creative. Classification: writes to Studio, destructive. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), creativeId (required), dryRun, seatId, +20 more. Returns: data, meta, error, status, +1 more
build_adCreate AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview.AIdempotentInspect
Create AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
build_campaign_creative_setPlan and create an initial Studio creative set for a campaign that has no saved creatives. Do not use this tool to rebuild existing creatives; use build_ad with campaignId or campaignName, which resolves and rebuilds the full saved Studio inventory.AIdempotentInspect
Plan and create an initial Studio creative set for a campaign that has no saved creatives. Do not use this tool to rebuild existing creatives; use build_ad with campaignId or campaignName, which resolves and rebuilds the full saved Studio inventory.. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: KPI (required), audience (required), objective (required), funnelStage (required), +36 more. Returns: data, meta, error, status, +1 more
build_creative_osDesign, render and save a review-held editable scratch Display or Social working version using Creative OS.BIdempotentInspect
Design, render and save a review-held editable scratch Display or Social working version using Creative OS.. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), campaignId (required), creativeId (required), advertiserId (required), +24 more. Returns: data, meta, error, status, +1 more
build_doohBuild a DOOH-native poster for an existing Studio creative, compare exact native renders and save the complete editable working version by default. Below-threshold creative review retains a technically valid version without release approval. Explicit saveToStudio=false is an unsaved preview. DOOH never contains CTA buttons. It does not route through Display build_ad.AIdempotentInspect
Build a DOOH-native poster for an existing Studio creative, compare exact native renders and save the complete editable working version by default. Below-threshold creative review retains a technically valid version without release approval. Explicit saveToStudio=false is an unsaved preview. DOOH never contains CTA buttons. It does not route through Display build_ad.. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: copy, assets, format, seatId, +33 more. Returns: data, meta, error, status, +1 more
build_videoadCreate an advertiser-aware pre-roll, CTV, or native Social video composition with varied executable scene layouts and channel constraints. It never claims an MP4 master or traffic-ready asset before Studio has rendered and certified one.AIdempotentInspect
Create an advertiser-aware pre-roll, CTV, or native Social video composition with varied executable scene layouts and channel constraints. It never claims an MP4 master or traffic-ready asset before Studio has rendered and certified one.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: channel (required), objective (required), cta, offer, +45 more. Returns: data, meta, error, status, +1 more
build_world_research_profileBuild a versioned advertiser research graph from configured identity and approved context.CIdempotentInspect
Build a versioned advertiser research graph from configured identity and approved context.. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: seatId, seatName, advertiserId, sourceLocale, +12 more. Returns: data, meta, error, status, +1 more
cancel_taskcancel taskDIdempotentInspect
cancel task. Classification: read-only. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: taskId (required), reason, seatId, seatName, +14 more. Returns: data, meta, error, status, +1 more
clone_creativeclone creativeCIdempotentInspect
clone creative. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), creativeId (required), idempotencyKey (required), dryRun, +16 more. Returns: data, meta, error, status, +1 more
create_advertisercreate advertiserBIdempotentInspect
create advertiser. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), advertiser (required), idempotencyKey (required), dryRun, +16 more. Returns: data, meta, error, status, +1 more
create_campaignCreate a Studio campaign. Put all campaign fields inside campaign. Map natural-language requests such as "called" to campaignName, awareness/consideration/conversion to funnelStage, impression goals to targetImpressions, Social delivery goals to socialImpressions, and KPI labels to primaryKpi or secondaryKpi.AIdempotentInspect
Create a Studio campaign. Put all campaign fields inside campaign. Map natural-language requests such as "called" to campaignName, awareness/consideration/conversion to funnelStage, impression goals to targetImpressions, Social delivery goals to socialImpressions, and KPI labels to primaryKpi or secondaryKpi.. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: campaign (required), idempotencyKey (required), dryRun, seatId, +16 more. Returns: data, meta, error, status, +1 more
create_creative_briefGenerate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal.AIdempotentInspect
Generate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal.. Classification: writes to Studio, creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
create_creative_intelligence_planCreate a concise proposed campaign plan from one grounded opportunity. Studio approval is required before campaign creation.BIdempotentInspect
Create a concise proposed campaign plan from one grounded opportunity. Studio approval is required before campaign creation.. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: advertiserId (required), opportunityId (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
create_creative_versioncreate creative versionBIdempotentInspect
create creative version. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), creativeId (required), idempotencyKey (required), dryRun, +19 more. Returns: data, meta, error, status, +1 more
create_flightcreate flightCIdempotentInspect
create flight. Classification: writes to Studio. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: name, dryRun, seatId, flightId, +22 more. Returns: data, meta, error, status, +1 more
create_production_plancreate production planCIdempotentInspect
create production plan. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: brand (required), brief (required), format (required), campaignName (required), +25 more. Returns: data, meta, error, status, +1 more
delete_flightdelete flightCDestructiveIdempotentInspect
delete flight. Classification: writes to Studio, destructive. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), accountId (required), dryRun, seatId, +20 more. Returns: data, meta, error, status, +1 more
export_creativeExport an existing persisted Studio CreativeDocument version to JPEG, PNG, or a version-bound HTML5 ZIP. HTML5 supports only the declared platform packaging profiles and does not generate or replace editable creative state.AIdempotentInspect
Export an existing persisted Studio CreativeDocument version to JPEG, PNG, or a version-bound HTML5 ZIP. HTML5 supports only the declared platform packaging profiles and does not generate or replace editable creative state.. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
export_trafficked_assetsexport trafficked assetsCRead-onlyIdempotentInspect
export trafficked assets. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), type, seatId, seatName, +13 more. Returns: data, meta, error, status, +1 more
generate_adserver_taggenerate adserver tagCIdempotentInspect
generate adserver tag. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), creativeId (required), force, seatId, +17 more. Returns: data, meta, error, status, +1 more
generate_preview_linksGenerate public review preview links for one or more saved Studio creatives without changing campaign content.CRead-onlyIdempotentInspect
Generate public review preview links for one or more saved Studio creatives without changing campaign content.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: accountId (required), seatId, seatName, creativeId, +14 more. Returns: data, meta, error, status, +1 more
get_adserver_tagget adserver tagCRead-onlyIdempotentInspect
get adserver tag. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), creativeId (required), force, seatId, +17 more. Returns: data, meta, error, status, +1 more
get_advertiserget advertiserCRead-onlyIdempotentInspect
get advertiser. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: advertiserId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_assetget assetARead-onlyIdempotentInspect
get asset. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. Studio assets are scoped resources: pass advertiserId or creativeId when listing assets, and pass one of those scopes together with assetId when retrieving one asset. LeanrIQ returns INVALID_INPUT rather than a misleading empty result when that scope is absent.
Inputs: assetId (required), seatId, taskId, flightId, +19 more. Returns: data, meta, error, status, +1 more
get_brand_profileResearch and return a LeanrIQ brand profile. This read capability does not save to Studio.BRead-onlyIdempotentInspect
Research and return a LeanrIQ brand profile. This read capability does not save to Studio.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brandUrl (required), brandName (required), seatId, seatName, +16 more. Returns: data, meta, error, status, +1 more
get_brand_visualsCollect brand logos, imagery, colours, fonts, and visual previews for use in Studio creative builds. Use this before build_ad when a campaign needs visual grounding; this read capability does not save to Studio.BRead-onlyIdempotentInspect
Collect brand logos, imagery, colours, fonts, and visual previews for use in Studio creative builds. Use this before build_ad when a campaign needs visual grounding; this read capability does not save to Studio.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brandName (required), websiteUrl (required), advertiserId (required), seatId, +15 more. Returns: data, meta, error, status, +1 more
get_campaignget campaignARead-onlyIdempotentInspect
get campaign. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. Campaign metadata only. Studio aiActivation/adBuild fields describe workflow or progress state, not saved creative inventory, and must never be used to infer whether creatives exist or how many are saved. If the user asks for creatives or creative inventory for a known campaignId, call list_creatives directly; do not preflight get_campaign.
Inputs: campaignId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_capabilitiesget capabilitiesCRead-onlyIdempotentInspect
get capabilities. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, sourceLocale, targetMarket, +11 more. Returns: data, meta, error, status, +1 more
get_competitor_intelligenceRead saved canonical LeanrIQ Competitor Intelligence V2 for an advertiser-scoped competitor. This does not reacquire evidence or generate new recommendations.ARead-onlyIdempotentInspect
Read saved canonical LeanrIQ Competitor Intelligence V2 for an advertiser-scoped competitor. This does not reacquire evidence or generate new recommendations.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, website, reportId, seatName, +17 more. Returns: data, meta, error, status, +1 more
get_creativeget creativeCRead-onlyIdempotentInspect
get creative. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: creativeId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_creative_intelligenceRead saved advertiser creative opportunities and source provenance.CRead-onlyIdempotentInspect
Read saved advertiser creative opportunities and source provenance.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: advertiserId (required), seatId, seatName, sourceLocale, +11 more. Returns: data, meta, error, status, +1 more
get_creative_intelligence_runRead an exact durable intelligence run, including stage, terminal state and retry metadata.CRead-onlyIdempotentInspect
Read an exact durable intelligence run, including stage, terminal state and retry metadata.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: runId (required), advertiserId (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
get_current_seatget current seatCRead-onlyIdempotentInspect
get current seat. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, sourceLocale, targetMarket, +10 more. Returns: data, meta, error, status, +1 more
get_current_userget current userCRead-onlyIdempotentInspect
get current user. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, sourceLocale, targetMarket, +10 more. Returns: data, meta, error, status, +1 more
get_flightget flightCRead-onlyIdempotentInspect
get flight. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_leanriq_capabilitiesDescribe the LeanrIQ outcomes available to this caller, its current capability profile, safe starting action, and effective build/Studio/publish boundaries. This is concise discovery, not a raw tool-registry dump.BRead-onlyIdempotentInspect
Describe the LeanrIQ outcomes available to this caller, its current capability profile, safe starting action, and effective build/Studio/publish boundaries. This is concise discovery, not a raw tool-registry dump.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, sourceLocale, targetMarket, +10 more. Returns: data, meta, error, status, +1 more
get_media_buy_deliveryAdCP-standard media-buy delivery reporting.CRead-onlyIdempotentInspect
AdCP-standard media-buy delivery reporting.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: media_buy_ids (required), ext, seatId, account, +23 more. Returns: data, meta, error, status, +1 more
get_permissionsget permissionsCRead-onlyIdempotentInspect
get permissions. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, accountId, sourceLocale, +11 more. Returns: data, meta, error, status, +1 more
get_preview_linkget preview linkCRead-onlyIdempotentInspect
get preview link. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: previewId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_taskPoll a durable LeanrIQ task returned by build_ad, revise_creative, trafficking, or another queued capability and continue with the completed output.BRead-onlyIdempotentInspect
Poll a durable LeanrIQ task returned by build_ad, revise_creative, trafficking, or another queued capability and continue with the completed output.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: taskId (required), seatId, seatName, sourceLocale, +11 more. Returns: data, meta, error, status, +1 more
get_templateget templateCRead-onlyIdempotentInspect
get template. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: templateId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_trafficked_assetsget trafficked assetsCRead-onlyIdempotentInspect
get trafficked assets. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
get_vertical_intelligenceget vertical intelligenceCRead-onlyIdempotentInspect
get vertical intelligence. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
get_world_activation_evidenceRead scoped verified event attestations for Studio approval and activation; no publication authority.CRead-onlyIdempotentInspect
Read scoped verified event attestations for Studio approval and activation; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: eventIds (required), seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
get_world_intelligenceGet the latest advertiser World Intelligence summary. It is fresh, source-backed context that may be partial; opportunities are recommendations and this never publishes creative.CRead-onlyIdempotentInspect
Get the latest advertiser World Intelligence summary. It is fresh, source-backed context that may be partial; opportunities are recommendations and this never publishes creative.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: runId, seatId, seatName, startedAt, +13 more. Returns: data, meta, error, status, +1 more
get_world_opportunityGet one active or historical World Intelligence opportunity and its compact provenance in the selected advertiser scope. It does not publish creative.BRead-onlyIdempotentInspect
Get one active or historical World Intelligence opportunity and its compact provenance in the selected advertiser scope. It does not publish creative.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: opportunityId (required), seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
get_world_research_decisionRead advertiser-scoped World Intelligence V3 decision with evidence; no publication authority.BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 decision with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_eventRead advertiser-scoped World Intelligence V3 event with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 event with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_eventsRead advertiser-scoped World Intelligence V3 events with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 events with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_insightsRead advertiser-scoped World Intelligence V3 insights with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 insights with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_mentionsRead advertiser-scoped World Intelligence V3 mentions with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 mentions with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_profileRead advertiser-scoped World Intelligence V3 profile with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 profile with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_proposalRead advertiser-scoped World Intelligence V3 proposal with evidence; no publication authority.BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 proposal with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_questionRead advertiser-scoped World Intelligence V3 question with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 question with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
get_world_research_summaryRead advertiser-scoped World Intelligence V3 summary with evidence; no publication authority.CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 summary with evidence; no publication authority.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
launch_creative_campaignLeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions.BIdempotentInspect
LeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions.. Classification: writes to Studio, creates billable AI usage, publishes externally. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: objective (required), KPI, cta, tone, +59 more. Returns: data, meta, error, status, +1 more
leanr_build_campaign_creative_setPlan and create an initial Studio creative set for a campaign that has no saved creatives. Do not use this tool to rebuild existing creatives; use build_ad with campaignId or campaignName, which resolves and rebuilds the full saved Studio inventory. (deprecated alias)AIdempotentInspect
Plan and create an initial Studio creative set for a campaign that has no saved creatives. Do not use this tool to rebuild existing creatives; use build_ad with campaignId or campaignName, which resolves and rebuilds the full saved Studio inventory.. Deprecated alias for build_campaign_creative_set. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: KPI (required), audience (required), objective (required), funnelStage (required), +36 more. Returns: data, meta, error, status, +1 more
leanriq_build_adCreate AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview. (deprecated alias)AIdempotentInspect
Create AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview.. Deprecated alias for build_ad. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
leanriq_build_agent_adCreate AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview. (deprecated alias)AIdempotentInspect
Create AI Display CreativeDocuments from objective and requestedFormats without pre-existing creatives. Optional outputs requests static JPEG/PNG delivery after save_to_studio while retaining the editable document. Export existing versions with export_creative. Build and save existing Studio creative records. When campaignId or campaignName is supplied, LeanrIQ resolves the complete persisted campaign inventory, uses each saved brief, approved asset set, and eligible global or advertiser template, then runs the canonical Studio Gold build path. Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview.. Deprecated alias for build_ad. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
leanriq_build_doohBuild a DOOH-native poster for an existing Studio creative, compare exact native renders and save the complete editable working version by default. Below-threshold creative review retains a technically valid version without release approval. Explicit saveToStudio=false is an unsaved preview. DOOH never contains CTA buttons. It does not route through Display build_ad. (deprecated alias)AIdempotentInspect
Build a DOOH-native poster for an existing Studio creative, compare exact native renders and save the complete editable working version by default. Below-threshold creative review retains a technically valid version without release approval. Explicit saveToStudio=false is an unsaved preview. DOOH never contains CTA buttons. It does not route through Display build_ad.. Deprecated alias for build_dooh. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: copy, assets, format, seatId, +33 more. Returns: data, meta, error, status, +1 more
leanriq_build_world_research_profileBuild a versioned advertiser research graph from configured identity and approved context. (deprecated alias)CIdempotentInspect
Build a versioned advertiser research graph from configured identity and approved context.. Deprecated alias for build_world_research_profile. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: seatId, seatName, advertiserId, sourceLocale, +12 more. Returns: data, meta, error, status, +1 more
leanriq_campaign_builderBuild a campaign in the LeanrIQ Creative CockpitAIdempotentInspect
One-prompt campaign builder with an interactive MCP App. Phase territories creates three distinct AI creative territories from the campaign objective. Phase build executes the selected territory through the canonical run_creative_chain, saves real Studio creatives, builds ads, returns previews and QA evidence, and never publishes media. A LeanrIQ seat is required; idempotencyKey is required for the build phase. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brand (required), product (required), audience (required), objective (required), +12 more. Returns: data, meta, error, status, +1 more
leanriq_create_briefGenerate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal. (deprecated alias)AIdempotentInspect
Generate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal.. Deprecated alias for create_creative_brief. Classification: writes to Studio, creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
leanriq_create_creative_briefGenerate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal. (deprecated alias)AIdempotentInspect
Generate Studio-ready design briefs for one or more creatives, using campaign context, brand rules, audience, offer, and format constraints. When creative IDs and saveToStudio are supplied, LeanrIQ saves only when the caller has Studio write permission; otherwise it returns a non-destructive proposal.. Deprecated alias for create_creative_brief. Classification: writes to Studio, creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
leanriq_create_creative_intelligence_planCreate a concise proposed campaign plan from one grounded opportunity. Studio approval is required before campaign creation. (deprecated alias)CIdempotentInspect
Create a concise proposed campaign plan from one grounded opportunity. Studio approval is required before campaign creation.. Deprecated alias for create_creative_intelligence_plan. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: advertiserId (required), opportunityId (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
leanriq_create_production_plancreate production plan (deprecated alias)AIdempotentInspect
create production plan. Deprecated alias for create_production_plan. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: brand (required), brief (required), format (required), campaignName (required), +25 more. Returns: data, meta, error, status, +1 more
leanriq_create_strategycreate creative strategy (deprecated alias)AIdempotentInspect
create creative strategy. Deprecated alias for create_creative_strategy. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: goal (required), brand (required), product (required), audience (required), +18 more. Returns: data, meta, error, status, +1 more
leanriq_current_seatGet active seatARead-onlyIdempotentInspect
Purpose: show the currently active LeanrIQ seat for the authenticated user. Output: returns the active seat and allowed seat list. Exact-ID read tools can resolve a unique authorised seat server-side. Select or pass a seat when you want to force a workspace, when a write is requested, or when LeanrIQ asks you to disambiguate. Constraints: read-only helper tool. Failure cases: AUTH_REQUIRED, SEAT_ACCESS_DENIED. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: no named parameters. Returns: data, meta, error, status, +1 more
leanriq_get_brand_profileResearch and return a LeanrIQ brand profile. This read capability does not save to Studio. (deprecated alias)BRead-onlyIdempotentInspect
Research and return a LeanrIQ brand profile. This read capability does not save to Studio.. Deprecated alias for get_brand_profile. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brandUrl (required), brandName (required), seatId, seatName, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_brand_visualsCollect brand logos, imagery, colours, fonts, and visual previews for use in Studio creative builds. Use this before build_ad when a campaign needs visual grounding; this read capability does not save to Studio. (deprecated alias)BRead-onlyIdempotentInspect
Collect brand logos, imagery, colours, fonts, and visual previews for use in Studio creative builds. Use this before build_ad when a campaign needs visual grounding; this read capability does not save to Studio.. Deprecated alias for get_brand_visuals. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brandName (required), websiteUrl (required), advertiserId (required), seatId, +15 more. Returns: data, meta, error, status, +1 more
leanriq_get_competitor_creative_intelligenceRun canonical LeanrIQ Competitor Intelligence V2 for one advertiser-scoped competitor. Defaults match Studio: 90-day DISPLAY evidence and no mixed social/video banner inference. Without forceRefresh, an existing canonical result is reused when available. (deprecated alias)AIdempotentInspect
Run canonical LeanrIQ Competitor Intelligence V2 for one advertiser-scoped competitor. Defaults match Studio: 90-day DISPLAY evidence and no mixed social/video banner inference. Without forceRefresh, an existing canonical result is reused when available.. Deprecated alias for run_competitor_intelligence. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: name, limit, domain, market, +34 more. Returns: data, meta, error, status, +1 more
leanriq_get_creative_intelligenceRead saved advertiser creative opportunities and source provenance. (deprecated alias)ARead-onlyIdempotentInspect
Read saved advertiser creative opportunities and source provenance.. Deprecated alias for get_creative_intelligence. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: advertiserId (required), seatId, seatName, sourceLocale, +11 more. Returns: data, meta, error, status, +1 more
leanriq_get_creative_intelligence_runRead an exact durable intelligence run, including stage, terminal state and retry metadata. (deprecated alias)BRead-onlyIdempotentInspect
Read an exact durable intelligence run, including stage, terminal state and retry metadata.. Deprecated alias for get_creative_intelligence_run. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: runId (required), advertiserId (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
leanriq_get_vertical_intelligenceget vertical intelligence (deprecated alias)CRead-onlyIdempotentInspect
get vertical intelligence. Deprecated alias for get_vertical_intelligence. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: brief, force, input, assets, +36 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_activation_evidenceRead scoped verified event attestations for Studio approval and activation; no publication authority. (deprecated alias)BRead-onlyIdempotentInspect
Read scoped verified event attestations for Studio approval and activation; no publication authority.. Deprecated alias for get_world_activation_evidence. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: eventIds (required), seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_intelligenceGet the latest advertiser World Intelligence summary. It is fresh, source-backed context that may be partial; opportunities are recommendations and this never publishes creative. (deprecated alias)BRead-onlyIdempotentInspect
Get the latest advertiser World Intelligence summary. It is fresh, source-backed context that may be partial; opportunities are recommendations and this never publishes creative.. Deprecated alias for get_world_intelligence. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: runId, seatId, seatName, startedAt, +13 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_opportunityGet one active or historical World Intelligence opportunity and its compact provenance in the selected advertiser scope. It does not publish creative. (deprecated alias)ARead-onlyIdempotentInspect
Get one active or historical World Intelligence opportunity and its compact provenance in the selected advertiser scope. It does not publish creative.. Deprecated alias for get_world_opportunity. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: opportunityId (required), seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_decisionRead advertiser-scoped World Intelligence V3 decision with evidence; no publication authority. (deprecated alias)BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 decision with evidence; no publication authority.. Deprecated alias for get_world_research_decision. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_eventRead advertiser-scoped World Intelligence V3 event with evidence; no publication authority. (deprecated alias)CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 event with evidence; no publication authority.. Deprecated alias for get_world_research_event. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_eventsRead advertiser-scoped World Intelligence V3 events with evidence; no publication authority. (deprecated alias)BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 events with evidence; no publication authority.. Deprecated alias for get_world_research_events. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_insightsRead advertiser-scoped World Intelligence V3 insights with evidence; no publication authority. (deprecated alias)CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 insights with evidence; no publication authority.. Deprecated alias for get_world_research_insights. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_mentionsRead advertiser-scoped World Intelligence V3 mentions with evidence; no publication authority. (deprecated alias)ARead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 mentions with evidence; no publication authority.. Deprecated alias for get_world_research_mentions. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_profileRead advertiser-scoped World Intelligence V3 profile with evidence; no publication authority. (deprecated alias)ARead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 profile with evidence; no publication authority.. Deprecated alias for get_world_research_profile. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_proposalRead advertiser-scoped World Intelligence V3 proposal with evidence; no publication authority. (deprecated alias)CRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 proposal with evidence; no publication authority.. Deprecated alias for get_world_research_proposal. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_questionRead advertiser-scoped World Intelligence V3 question with evidence; no publication authority. (deprecated alias)BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 question with evidence; no publication authority.. Deprecated alias for get_world_research_question. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_get_world_research_summaryRead advertiser-scoped World Intelligence V3 summary with evidence; no publication authority. (deprecated alias)BRead-onlyIdempotentInspect
Read advertiser-scoped World Intelligence V3 summary with evidence; no publication authority.. Deprecated alias for get_world_research_summary. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, entity, seatId, eventId, +16 more. Returns: data, meta, error, status, +1 more
leanriq_launch_creative_campaignLeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions. (deprecated alias)AIdempotentInspect
LeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions.. Deprecated alias for launch_creative_campaign. Classification: writes to Studio, creates billable AI usage, publishes externally. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: objective (required), KPI, cta, tone, +59 more. Returns: data, meta, error, status, +1 more
leanriq_list_world_opportunitiesList active World Intelligence creative opportunities for one authorised advertiser. Opportunities are human-review recommendations and never publish creative. (deprecated alias)ARead-onlyIdempotentInspect
List active World Intelligence creative opportunities for one authorised advertiser. Opportunities are human-review recommendations and never publish creative.. Deprecated alias for list_world_opportunities. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
leanriq_list_world_signalsList active, source-provenanced World Intelligence signals for one authorised advertiser. This is current contextual intelligence, not a general-purpose news search. (deprecated alias)BRead-onlyIdempotentInspect
List active, source-provenanced World Intelligence signals for one authorised advertiser. This is current contextual intelligence, not a general-purpose news search.. Deprecated alias for list_world_signals. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
leanriq_qa_creativeQA a creative for launch readiness with actionable issues, certification evidence, and next steps before preview, revision, or trafficking. (deprecated alias)AIdempotentInspect
QA a creative for launch readiness with actionable issues, certification evidence, and next steps before preview, revision, or trafficking.. Deprecated alias for qa_creative. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: brand (required), format (required), creative (required), objective (required), +16 more. Returns: data, meta, error, status, +1 more
leanriq_recommend_workflowRecommend the shortest LeanrIQ workflowARead-onlyIdempotentInspect
Purpose: choose the shortest safe LeanrIQ creative/adtech workflow when the caller is unsure which capability to use. Use only for ambiguous requests; do not call this before every LeanrIQ action. Output: one outcome journey, preferred capability, minimal call plan, completion evidence and approval boundary. Read-only and non-mutating. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: intent (required), knownIds. Returns: data, meta, error, status, +1 more
leanriq_record_world_research_feedbackRecord reviewed relevance or decision feedback without changing approval or safety constraints. (deprecated alias)CIdempotentInspect
Record reviewed relevance or decision feedback without changing approval or safety constraints.. Deprecated alias for record_world_research_feedback. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: eventId (required), outcome (required), reason, seatId, +14 more. Returns: data, meta, error, status, +1 more
leanriq_resolve_or_provision_advertiserresolve or provision advertiser (deprecated alias)BIdempotentInspect
resolve or provision advertiser. Deprecated alias for resolve_or_provision_advertiser. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brand, dryRun, seatId, billing, +19 more. Returns: data, meta, error, status, +1 more
leanriq_run_creative_chainrun creative chain (deprecated alias)BIdempotentInspect
run creative chain. Deprecated alias for run_creative_chain. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: KPI, goal, tone, brand, +38 more. Returns: data, meta, error, status, +1 more
leanriq_run_creative_intelligenceSynthesize grounded, deduplicated advertiser creative opportunities from automatic competitor/category research and broad World signals. Returns a durable run ID and honest partial states; creates no campaign or publication. (deprecated alias)AIdempotentInspect
Synthesize grounded, deduplicated advertiser creative opportunities from automatic competitor/category research and broad World signals. Returns a durable run ID and honest partial states; creates no campaign or publication.. Deprecated alias for run_creative_intelligence. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: advertiserId (required), idempotencyKey (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
leanriq_run_world_intelligenceRun bounded, current World Intelligence for one authorised advertiser. It returns source-backed external context and creative opportunities; evidence may be partial and it never publishes or activates creative. (deprecated alias)BIdempotentInspect
Run bounded, current World Intelligence for one authorised advertiser. It returns source-backed external context and creative opportunities; evidence may be partial and it never publishes or activates creative.. Deprecated alias for run_world_intelligence. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: preserve_qualified_evidence_and_signals. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: policy, seatId, routine, seatName, +18 more. Returns: data, meta, error, status, +1 more
leanriq_select_seatSelect active seatAIdempotentInspect
Purpose: select an allowed LeanrIQ seat for subsequent seat-scoped operations. Output: returns the selected seat and allowed seat list. Exact-ID read tools can resolve a unique authorised seat server-side. Select or pass a seat when you want to force a workspace, when a write is requested, or when LeanrIQ asks you to disambiguate. Constraints: only authenticated seats already granted to the user can be selected. Failure cases: AUTH_REQUIRED, SEAT_ACCESS_DENIED. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: seatId, seatName. Returns: data, meta, error, status, +1 more
leanriq_select_world_opportunity_for_campaignExplicitly select one reviewed, source-provenanced World Intelligence opportunity for an authorised Studio campaign. Studio performs the same campaign authorization, scoped LeanrIQ lookup, and persistence path as the UI. This does not materialise a feed, create creative, traffic, or publish. (deprecated alias)AIdempotentInspect
Explicitly select one reviewed, source-provenanced World Intelligence opportunity for an authorised Studio campaign. Studio performs the same campaign authorization, scoped LeanrIQ lookup, and persistence path as the UI. This does not materialise a feed, create creative, traffic, or publish.. Deprecated alias for select_world_opportunity_for_campaign. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: campaignId (required), advertiserId (required), opportunityId (required), idempotencyKey (required), +18 more. Returns: data, meta, error, status, +1 more
list_accessible_seatslist accessible seatsDRead-onlyIdempotentInspect
list accessible seats. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: seatId, seatName, sourceLocale, targetMarket, +10 more. Returns: data, meta, error, status, +1 more
list_advertiserslist advertisersCRead-onlyIdempotentInspect
list advertisers. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_assetslist assetsBRead-onlyIdempotentInspect
list assets. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. Studio assets are scoped resources: pass advertiserId or creativeId when listing assets, and pass one of those scopes together with assetId when retrieving one asset. LeanrIQ returns INVALID_INPUT rather than a misleading empty result when that scope is absent.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_campaignslist campaignsCRead-onlyIdempotentInspect
list campaigns. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_competitor_evidenceList qualified display evidence from saved canonical LeanrIQ Competitor Intelligence V2. Cross-channel inspiration is not mixed into DISPLAY evidence.CRead-onlyIdempotentInspect
List qualified display evidence from saved canonical LeanrIQ Competitor Intelligence V2. Cross-channel inspiration is not mixed into DISPLAY evidence.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, seatId, website, reportId, +18 more. Returns: data, meta, error, status, +1 more
list_competitorslist competitorsCRead-onlyIdempotentInspect
list competitors. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_creativesList Studio creatives. Prefer campaignId for deterministic campaign inventory reads. If only campaignName is available, pair it with advertiserId or advertiserName so LeanrIQ can resolve the campaign once, follow pagination centrally, and return the full campaign creative set without local guesswork.ARead-onlyIdempotentInspect
List Studio creatives. Prefer campaignId for deterministic campaign inventory reads. If only campaignName is available, pair it with advertiserId or advertiserName so LeanrIQ can resolve the campaign once, follow pagination centrally, and return the full campaign creative set without local guesswork.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. This tool is the authoritative saved Studio creative inventory for the requested scope. With an exact campaignId, call list_creatives directly as the first and only inventory read. The MCP response returns a compact inventory containing creative names, IDs, sizes and statuses; use get_creative only when full creative internals are needed. Non-empty rows prove saved creatives exist regardless of campaign build or activation workflow state; a completed empty result is authoritative. Do not call get_campaign first to decide whether creatives exist.
Inputs: limit, cursor, seatId, status, +19 more. Returns: data, meta, error, status, +1 more
list_creative_versionslist creative versionsCRead-onlyIdempotentInspect
list creative versions. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: creativeId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
list_flightslist flightsCRead-onlyIdempotentInspect
list flights. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_taskslist tasksCRead-onlyIdempotentInspect
list tasks. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_templateslist templatesCRead-onlyIdempotentInspect
list templates. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, cursor, seatId, status, +17 more. Returns: data, meta, error, status, +1 more
list_world_opportunitiesList active World Intelligence creative opportunities for one authorised advertiser. Opportunities are human-review recommendations and never publish creative.BRead-onlyIdempotentInspect
List active World Intelligence creative opportunities for one authorised advertiser. Opportunities are human-review recommendations and never publish creative.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
list_world_signalsList active, source-provenanced World Intelligence signals for one authorised advertiser. This is current contextual intelligence, not a general-purpose news search.ARead-onlyIdempotentInspect
List active, source-provenanced World Intelligence signals for one authorised advertiser. This is current contextual intelligence, not a general-purpose news search.. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: limit, seatId, seatName, advertiserId, +12 more. Returns: data, meta, error, status, +1 more
preview_trafficking_outputpreview trafficking outputCRead-onlyIdempotentInspect
preview trafficking output. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), accountId (required), force, dryRun, +17 more. Returns: data, meta, error, status, +1 more
promote_creative_workspaceDeliberately promote one approved LeanrIQ creative workspace into Studio. The workspace and selected territory are retained, and a repeated promotion returns the recorded result rather than duplicating Studio production records.AIdempotentInspect
Deliberately promote one approved LeanrIQ creative workspace into Studio. The workspace and selected territory are retained, and a repeated promotion returns the recorded result rather than duplicating Studio production records.. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: workspaceId (required), seatId, seatName, accountId, +17 more. Returns: data, meta, error, status, +1 more
provide_performance_feedbackprovide performance feedbackCIdempotentInspect
provide performance feedback. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: feedback (required), accountId (required), idempotencyKey (required), seatId, +15 more. Returns: data, meta, error, status, +1 more
push_flight_to_yahooPublish path for approved work only: traffick and certify a saved Studio flight, generate or reuse ad-server tags, and push the resulting inactive or approved payload to Yahoo DSP with audit evidence.BIdempotentInspect
Publish path for approved work only: traffick and certify a saved Studio flight, generate or reuse ad-server tags, and push the resulting inactive or approved payload to Yahoo DSP with audit evidence.. Classification: writes to Studio, publishes externally. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), idempotencyKey (required), seatId, seatName, +15 more. Returns: data, meta, error, status, +1 more
qa_creativeQA a creative for launch readiness with actionable issues, certification evidence, and next steps before preview, revision, or trafficking.BIdempotentInspect
QA a creative for launch readiness with actionable issues, certification evidence, and next steps before preview, revision, or trafficking.. Classification: creates billable AI usage. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: brand (required), format (required), creative (required), objective (required), +16 more. Returns: data, meta, error, status, +1 more
record_world_research_feedbackRecord reviewed relevance or decision feedback without changing approval or safety constraints.CIdempotentInspect
Record reviewed relevance or decision feedback without changing approval or safety constraints.. Classification: read-only. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: eventId (required), outcome (required), reason, seatId, +14 more. Returns: data, meta, error, status, +1 more
refresh_brand_profileRefresh and save a standalone Studio advertiser brand profile.BIdempotentInspect
Refresh and save a standalone Studio advertiser brand profile.. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: brandUrl (required), accountId (required), brandName (required), advertiserId (required), +18 more. Returns: data, meta, error, status, +1 more
refresh_brand_visualsrefresh brand visualsCIdempotentInspect
refresh brand visuals. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), brandName (required), websiteUrl (required), advertiserId (required), +17 more. Returns: data, meta, error, status, +1 more
restore_creative_versionrestore creative versionCIdempotentInspect
restore creative version. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: accountId (required), versionId (required), creativeId (required), idempotencyKey (required), +19 more. Returns: data, meta, error, status, +1 more
retraffick_creativeretraffick creativeCIdempotentInspect
retraffick creative. Classification: publishes externally. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), accountId (required), creativeId (required), force, +17 more. Returns: data, meta, error, status, +1 more
retraffick_flightretraffick flightBIdempotentInspect
retraffick flight. Classification: publishes externally. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), accountId (required), force, dryRun, +17 more. Returns: data, meta, error, status, +1 more
retry_taskretry taskDIdempotentInspect
retry task. Classification: read-only. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: taskId (required), reason, seatId, seatName, +14 more. Returns: data, meta, error, status, +1 more
revise_creativeRevise an existing saved Studio creative by executing a requested change from plain-language instructions. Use this directly when the user supplies a creativeId and asks to change copy, imagery, layout, colours, typography, CTA, branding, or any other editable creative element: do not respond with a copy-paste instruction or ask the user to make the edit in Studio. The revision saves to Studio by default and returns fresh preview links plus QA/certification context; set dryRun only when the user explicitly asks for an unsaved preview.AIdempotentInspect
Revise an existing saved Studio creative by executing a requested change from plain-language instructions. Use this directly when the user supplies a creativeId and asks to change copy, imagery, layout, colours, typography, CTA, branding, or any other editable creative element: do not respond with a copy-paste instruction or ask the user to make the edit in Studio. The revision saves to Studio by default and returns fresh preview links plus QA/certification context; set dryRun only when the user explicitly asks for an unsaved preview.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: creativeId (required), idempotencyKey (required), dryRun, prompt, +20 more. Returns: data, meta, error, status, +1 more
run_competitor_intelligenceRun canonical LeanrIQ Competitor Intelligence V2 for one advertiser-scoped competitor. Defaults match Studio: 90-day DISPLAY evidence and no mixed social/video banner inference. Without forceRefresh, an existing canonical result is reused when available.BIdempotentInspect
Run canonical LeanrIQ Competitor Intelligence V2 for one advertiser-scoped competitor. Defaults match Studio: 90-day DISPLAY evidence and no mixed social/video banner inference. Without forceRefresh, an existing canonical result is reused when available.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work.
Inputs: name, limit, domain, market, +34 more. Returns: data, meta, error, status, +1 more
run_creative_chainrun creative chainBIdempotentInspect
run creative chain. Classification: writes to Studio, creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: KPI, goal, tone, brand, +38 more. Returns: data, meta, error, status, +1 more
run_creative_intelligenceSynthesize grounded, deduplicated advertiser creative opportunities from automatic competitor/category research and broad World signals. Returns a durable run ID and honest partial states; creates no campaign or publication.AIdempotentInspect
Synthesize grounded, deduplicated advertiser creative opportunities from automatic competitor/category research and broad World signals. Returns a durable run ID and honest partial states; creates no campaign or publication.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: advertiserId (required), idempotencyKey (required), seatId, seatName, +12 more. Returns: data, meta, error, status, +1 more
run_world_intelligenceRun bounded, current World Intelligence for one authorised advertiser. It returns source-backed external context and creative opportunities; evidence may be partial and it never publishes or activates creative.BIdempotentInspect
Run bounded, current World Intelligence for one authorised advertiser. It returns source-backed external context and creative opportunities; evidence may be partial and it never publishes or activates creative.. Classification: creates billable AI usage. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: preserve_qualified_evidence_and_signals. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: policy, seatId, routine, seatName, +18 more. Returns: data, meta, error, status, +1 more
select_world_opportunity_for_campaignExplicitly select one reviewed, source-provenanced World Intelligence opportunity for an authorised Studio campaign. Studio performs the same campaign authorization, scoped LeanrIQ lookup, and persistence path as the UI. This does not materialise a feed, create creative, traffic, or publish.AIdempotentInspect
Explicitly select one reviewed, source-provenanced World Intelligence opportunity for an authorised Studio campaign. Studio performs the same campaign authorization, scoped LeanrIQ lookup, and persistence path as the UI. This does not materialise a feed, create creative, traffic, or publish.. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: campaignId (required), advertiserId (required), opportunityId (required), idempotencyKey (required), +18 more. Returns: data, meta, error, status, +1 more
traffick_creativetraffick creativeCIdempotentInspect
traffick creative. Classification: publishes externally. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), accountId (required), creativeId (required), force, +17 more. Returns: data, meta, error, status, +1 more
traffick_flighttraffick flightBIdempotentInspect
traffick flight. Classification: publishes externally. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), accountId (required), force, dryRun, +17 more. Returns: data, meta, error, status, +1 more
update_advertiserupdate advertiserCIdempotentInspect
update advertiser. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: patch (required), accountId (required), advertiserId (required), idempotencyKey (required), +17 more. Returns: data, meta, error, status, +1 more
update_campaignUpdate a Studio campaign. Use the canonical campaign fields inside patch, including campaignName, funnelStage, targetImpressions, socialImpressions, primaryKpi, and secondaryKpi when those values are being changed.AIdempotentInspect
Update a Studio campaign. Use the canonical campaign fields inside patch, including campaignName, funnelStage, targetImpressions, socialImpressions, primaryKpi, and secondaryKpi when those values are being changed.. Classification: writes to Studio. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: patch (required), accountId (required), campaignId (required), idempotencyKey (required), +17 more. Returns: data, meta, error, status, +1 more
update_flightupdate flightCIdempotentInspect
update flight. Classification: writes to Studio. Execution: durable. Task support: optional. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.
Inputs: flightId (required), name, dryRun, seatId, +22 more. Returns: data, meta, error, status, +1 more
validate_flightvalidate flightCRead-onlyIdempotentInspect
validate flight. Classification: read-only. Execution: synchronous. Task support: forbidden. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action.
Inputs: flightId (required), seatId, taskId, assetId, +19 more. Returns: data, meta, error, status, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Creative intelligence for Meta, TikTok, Google Ads and Amazon DSP, in Claude and other MCP clients.
Ads MCP for Meta, Google Ads, TikTok, Snapchat and LinkedIn: stage launches and manage campaigns.
AI agents that manage paid ads on Meta, LinkedIn, and Google Ads from any MCP client.
On-brand AI image and video campaigns with persistent characters and products, from any MCP client.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables to plan, write, illustrate, and voice a full marketing campaign through an MCP pipeline that generates copy, moodboards, voiceovers, and images with automated guardrails and budget controls.-
- FlicenseNot gradedqualityCmaintenanceEnables users to build, edit, transfer, report on, and monitor ad campaigns across Meta, Google, TikTok, Snapchat, and other connected ad platforms from Claude, ChatGPT, and other MCP clients.-
- AlicenseNot gradedqualityCmaintenanceEnables clients to generate framework-led creative workflows from a brief, with randomly selected alternatives and optional candidate pools exposed through a single MCP tool.MIT

PaidSync MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI assistants to create, manage, and optimize advertising campaigns across 14 ad and measurement platforms through a single MCP endpoint, with over 530 executable tools.4MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.