Tool

Purpose

add_campaign_audience_prospects

Add people directly (no list) by prospect_ids, organization_ids and/or stage_keys — at least one required. On an active/paused campaign they START THE SEQUENCE IMMEDIATELY (outreach is sent). Returns enrolled/already_enrolled/reactivated counts and *_truncated flags when the 1000-person cap was hit.

add_deal_line_item

Add an active catalog item (offering_id) to an OPEN deal at an agreed unit_price in the deal's currency, with quantity (default 1) and scope. Returns {data: LineItem}.

add_deal_prospect

Link a prospect to a deal as a contact, with optional role and is_primary. Returns {data: DealContact[]} (all the deal's contacts).

add_prospects_to_list

Add prospects to a prospect list by their UUIDs.

agent_draft_create

Stage an action (e.g. send a nudge, upsert a CRM contact, export a CSV) as a PENDING draft in the workspace for the human to approve. The draft is persisted in max-agent's agent_action_drafts table; nothing runs until the human approves. Returns { draft_id, state:'pending', review_url }. AFTER CREATING, POST THE RETURNED review_url (or a link to the agent drafts view in the workspace UI) TO THE USER'S CHAT CHANNEL SO THEY CAN APPROVE. Use this whenever an agent wants to take a write action on the user's behalf but the user hasn't pre-authorized the specific instance.

agent_draft_get

Fetch one agent action draft by id, including its full payload, current state, audit trail, and any execution result. Use to inspect a specific draft before recommending approve/reject to the user.

agent_draft_list

List agent action drafts in the workspace, optionally filtered by state (pending/approved/rejected/executed/failed/canceled) and/or action_type. Paginated via { limit, cursor }. Returns { data: [...], next_cursor? }. Use to show the user what's awaiting their approval or to audit recently-executed actions.

apollo_add_more

Append more leads to an existing Apollo list (async). Re-runs the saved search for additional results.

apollo_create_list

LAST RESORT: create an Apollo-backed prospect list (async). Use only when getleads_create_list and the Explorium tools cannot serve the request, or the user explicitly asks for Apollo. People search → ingestion. Poll with wait_for_prospect_list.

approve_inbox_draft

Approve a drafted reply and send it in-thread via Unipile, setting the action's status to 'approved'. Optionally pass body to send an edited reply instead of the stored draft. Returns the updated {data: InboxAutopilotAction}. Fails with 404 (draft not found), 409 (action not in 'draft' status), or 400 SendReplyError (code CHAT_NOT_FOUND | ACCOUNT_NOT_FOUND | ACCOUNT_NOT_CONNECTED | NO_PROSPECT_EMAIL | SEND_FAILED).

approve_proposal

Approve a pending proposal and launch its draft campaign. SYNCHRONOUS — max-agent builds the prospect list, creates the campaign, and launches it (may take a while). Optionally pass modifications (titles, target_prospect_ids, campaign_name, campaign_description) to override the recommendation before launch; omit them to approve as-is. On success returns {data: SignalProposal (status 'launched', draft_campaign_id set), campaign_id}. Can fail with 402 (enrichment quota exceeded — proposal reverts to pending), 409 (not pending / already decided / expired), or 422 (no target prospects / no connected account).

archive_campaign

Archive a campaign (soft delete) — hidden from default views but restorable.

archive_chat

Archive a chat (soft delete). Messages remain, use archived=true filter to see them.

attach_campaign_audience_list

Attach a prospect list as included (default) or excluded, also while running. Unless enroll_now=false, an included list's new members are enrolled at once — on an active/paused campaign that starts outreach to them.

attach_campaign_to_intent_trigger

Link an existing campaign to up to 20 intent triggers so a changed signal auto-launches it. Idempotent. Returns {data: {attached, requested}}; 404 if the campaign or none of the triggers are in this workspace.

auto_create_organization_list

Create a saved company (organization) list from unified criteria (async). GetLeads first, Explorium as the fallback; Apollo is never used. Charges credits. Returns a pending list; poll with wait_for_prospect_list.

auto_create_prospect_list

Default way to source new people: create a prospect list from unified criteria (async). Runs GetLeads first and falls back to Explorium only when GetLeads can't express the filters (intent, departments, revenue, keywords) or finds nothing; Apollo is never used. Charges credits. Returns a pending list; poll with wait_for_prospect_list.

automation_activate

Publish the pending draft and arm its trigger — from now on it fires automatically on real records (422 with {details:[{step_id,message}]} if not runnable). A new webhook's one-time token is redacted. Returns {data: WorkflowDetail}.

automation_cancel_run

Cancel a queued or waiting (delayed) run; 409 if it already ran or is running. Returns {data: Run}.

automation_create

Create a workflow (unique name) with a first draft version; nothing fires until automation_activate. Returns {data: WorkflowDetail}.

automation_deactivate

Pause an active workflow: disarms its trigger; versions, runs and counters stay. Returns {data: WorkflowDetail}.

automation_delete

Permanently delete a workflow with all its versions and run history. Returns {data: {deleted: true}}.

automation_discard_draft

Archive the pending draft, keeping the active version (409 if there is no draft; 404 where the draft lifecycle is not enabled). Returns {data: Version}.

automation_get

Get one workflow with its draft_version and active_version documents and webhook_url. Returns {data: WorkflowDetail}.

automation_get_run

One run with per-step states, outputs and errors (403 for document-triggered runs without a member session). Returns {data: Run}.

automation_list

List the workspace's automation workflows with status, trigger, run counters and a summary of the draft/active version. Returns {data: Workflow[]}.

automation_list_runs

A workflow's run log, newest first, 25 per page. 403 if the page includes document-triggered runs (member session required). Returns {data: Run[], count}.

automation_list_versions

Every version of a workflow (draft, active, archived), newest first. Returns {data: Version[]}.

automation_resume

Re-arm a paused workflow's existing active version (never publishes a pending draft). Returns {data: WorkflowDetail}.

automation_run

Fire the workflow once, now, inline — runs the draft if one exists, else the active version — and REALLY executes its actions (tasks, campaign enrolls, webhooks, signature requests). Pass prospect_id for person-scoped manual triggers. Returns {data: Run}.

automation_save_draft

Replace the workflow's draft definition (creates a new draft if the latest version is active; the live version is untouched until automation_activate). Returns {data: Version}.

automation_update

Rename or redescribe a workflow (definition changes go through automation_save_draft). Returns {data: Workflow}.

book_meeting

Create a Cal.com booking and record it as a meeting. event_type_id defaults to the connection's default event type; start is a required ISO8601 UTC time; attendee_name, attendee_email, and attendee_time_zone (IANA) describe the attendee. Optionally pass recurrence_count (recurring event types), prospect_id (advances that prospect to 'replied'), campaign_id, and a flat string metadata map. Returns the created {data: meeting row} (calcom_booking_uid, meeting_url, status 'scheduled', etc.). Fails with 409 (no calendar connected), 400 (invalid body / no default event type), or 4xx/502 CALCOM_ERROR (e.g. slot conflict / instance unreachable).

bulk_create_intent_triggers

Create one monitor per member of a prospect_list_id (first 200) OR per organization_ids, sharing signal_type/platform/frequency/criteria/campaign_ids. Members with no URL for the platform are skipped, not fatal. Returns 201 {data: {created, skipped[{member_id, member_name, reason}], truncated}}; 422 if no member is monitorable or a linked campaign is not launch-ready.

bulk_delete_organizations

Delete multiple organizations. Set deleteProspects=true to cascade-delete linked prospects.

bulk_delete_prospects

Delete multiple prospects by IDs.

bulk_enrich

Queue many prospects and/or organizations for background enrichment by the cron worker (does NOT run inline). Provide prospect_ids and/or organization_ids. Returns {accepted} — how many rows were queued. Use this instead of calling enrich_prospect in a loop when enriching more than a couple of records.

bulk_get_campaign_node_run_counts

Node run counts for up to 100 campaigns in one call: { nodeRunCounts: { campaignId: { nodeId: count } } }. Inaccessible ids and campaigns with no runs are omitted.

bulk_import_organizations

Import multiple organizations. Deduplicates by domain. Returns imported/existing/failed counts.

bulk_import_prospects

Import multiple prospects at once. Deduplicates by email. Returns imported/existing/failed counts.

calendar_status

Return the workspace's Cal.com connection status. Returns {data: {connected: false}} when no instance is connected, or {data: CalendarStatus} (baseUrl, username, label, defaultEventTypeId, eventTypes) when connected. eventTypes may be [] if the instance is currently unreachable. The api_key is never returned.

cancel_meeting

Cancel a recorded meeting by its meetings.id UUID. If the meeting has a Cal.com booking uid it is cancelled on Cal.com first, then the row is marked cancelled. Optionally pass a reason. Irreversible; Cal.com notifies the attendee. Returns the updated {data: meeting row} with status 'cancelled'. Fails with 404 (unknown / not in this workspace), 409 (no calendar connected, only when a Cal.com cancel is needed), or 4xx/502 CALCOM_ERROR.

cancel_meeting_series

Cancel a recurring Cal.com series from one occurrence (meeting_id): scope 'remaining' (this and later occurrences) or 'series' (all), optional reason. Irreversible; Cal.com notifies every attendee. Returns {data: meeting row, meta: {scope, occurrence_count}}; 409 if the meeting is not part of a recurring series.

cancel_warmup

Stop a warm-up at the end of its paid period (no refund; ends immediately if unpaid). resume_warmup undoes a pending cancellation.

claire_deep_research

Multi-source background research on a named person or company. Returns recent activity, news, role context, company highlights, and proof points. Synchronous (may take 30-90s). Call this BEFORE crafting personalized outreach so the message reflects who the prospect actually is.

claire_enrich_person

Resolve one person to their current title, seniority, employer (with headcount), location, dated career history and education — and optionally their work email and phone. COSTS CREDITS ON EVERY CALL, including when nothing is found: narrowing sections changes what comes back, not what it costs, so do not call this to browse or to check whether someone exists. Identify them with a LinkedIn URL, a work email, or a name PLUS a company or domain; a bare name is refused, because it matches the wrong person and is billed anyway. Add 'contact' to sections only when you intend to reach out — it runs a paid email/phone waterfall on top of the profile. Known gaps: skills is usually empty and there is no buyer-intent data, so do not retry hoping to fill them.

claire_extract_prospects_from_url

Fetch a public URL (conference attendee list, team / about page, press release, panel announcement, etc.) and extract structured prospects (people / contacts) from it via Claire. Returns { prospects:[{ name, title, company, linkedin_url?, email?, ... }], source_url, extracted_count, claire_request_id? }. Use when the user pastes a URL and asks to 'find leads here' / 'build a list from this page'. Pair with create_prospect or import_prospect_list_csv to persist the result.

claire_find_competitors

Identify direct competitors of a company by URL. Returns a list of competing companies with descriptions and sources. Synchronous (typically 1-3 min). Use to expand a prospect list with similar companies or to ground competitive positioning in outreach.

claire_market_watch

Run a market-watch pass on a URL, optionally filtered by criteria (e.g. 'pricing', 'hiring', 'funding'). Returns a snapshot of detected signals. Use to inform outreach timing (e.g. just-funded companies) or to spot competitive moves.

claire_search

Free-text research query against Claire's hub. Use for quick lookups like industry trends, funding news, or any topic where you'd otherwise google. Synchronous — waits for Claire to finish and returns the result. Use mode='lite' for fast first-pass (default), 'full' for deeper multi-source.

clear_failed_requests

Drain the dead-letter queue. Returns the number of entries removed. Use after manually replaying or after resolving the upstream issue.

confirm_meeting

Accept a pending Cal.com booking request (status 'pending' in get_upcoming_meetings) by meeting_id. Cal.com notifies the attendee. Returns {data: meeting row} with status 'scheduled'; 409 MEETING_LIFECYCLE_CONFLICT if the meeting is not pending.

connect_calendar

Connect the workspace's self-hosted Cal.com instance so Max can read availability and book meetings. Validates the credentials by calling Cal.com listEventTypes before storing them. Pass base_url (the instance API base, e.g. https://cal.example.com or .../api/v2), api_key, and optionally default_event_type_id. Returns {data: CalendarStatus} with connected:true, baseUrl, username, label, defaultEventTypeId, and the list of eventTypes. The api_key is never returned.

create_calendar_event

Create an event directly on a synced Google/Outlook calendar (account_id; primary calendar unless calendar_id). Needs title and start_at (timed) or start_date (all-day); optional end_at/end_date, time_zone, body, location, attendees, recurrence. The provider may email invitations to attendees. Returns {data: provider event} whose id is the event_id for update/delete. For a Cal.com booking use book_meeting instead.

create_campaign

Create a new campaign in draft state. Requires name, included_lists, and accounts. Won't send until launched.

create_campaign_share_link

PUBLISHES the campaign: enables an 'anyone with the link' URL (/share/) viewable without login. Re-enables the same token if one existed. Owner or workspace admin only; confirm with the user first.

create_deal

Create a native Max deal. Requires name; defaults to the default pipeline's first open stage and EUR. prospect_ids links contacts (first = primary; required if created in a won stage). Returns {data: Deal}.

create_deal_pipeline

Create a deal pipeline seeded with the default stages (max 10 per workspace). Returns {data: Pipeline}.

create_deal_stage

Add a stage (column) to a deal pipeline (max 24): label, optional color, type, win_probability, position. Returns {data: Stage}.

create_deal_stage_rule

Add an entry rule to a deal stage: rule_action notify, assign or enroll_campaign (enrolls the deal's primary contact in a campaign, which sends outreach) with matching config. Returns {data: Rule}.

create_icp

Save a new ICP. Only name is required; criteria/profile can be filled later. 409 code name_taken on a duplicate name. Returns {data: Icp}.

create_intent_trigger

Set up a monitor that watches for a buying signal (funding, hiring, tech_stack, news, job_change, topic, or custom): either a specific target_url, or a person/organization's stored profile on a platform. Optionally set the re-poll frequency and campaigns to auto-launch when it fires. Returns the created {data: IntentTrigger}.

create_linkedin_prospect_list

Create a list filled by a people search run on a connected LinkedIn account (classic or Sales Navigator). No credits; no emails/phones returned. Async: returns the pending list — poll wait_for_prospect_list.

create_mailpool_order

CHARGES THE WORKSPACE: buys domains and pre-configured sending mailboxes from Mailpool (real supplier purchase; not reversible). Confirm domains, mailboxes and price with the user first (search_mailpool_domains, get_mailpool_pricing). Never retry blindly: on an error or timeout check list_mailpool_orders first. Returns {order_id, status, tokens_charged, warning}.

create_organization

Create a new organization/company record.

create_organization_share_link

PUBLISHES the organization: enables an 'anyone with the link' URL (/share/) viewable without login. Re-enables the same token if one existed. Owner or workspace admin only; confirm with the user first.

create_people_share_link

PUBLISHES the workspace's ENTIRE People database: anyone with the link (/share/{token}) can view it (contact details masked). Creates or re-enables. Admin only.

create_prospect

Create a single prospect. Deduplicates by email — returns existing row if email already exists.

create_prospect_intelligence_watchers

Ask Claire to propose recurring research watchers for a prospect and create up to 4 (as claire profile hooks, deduped against existing). Runs a Claire search (~2 min); later hook runs charge credits. 409 if a run is already in progress.

create_prospect_list

Create an empty platform prospect list. To source NEW leads into a list use auto_create_prospect_list (GetLeads → Explorium), or pin a provider in this order: getleads_create_list, then explorium_create_list, then apollo_create_list as a last resort.

create_prospect_list_share_link

PUBLISHES the list publicly: anyone with the link (/share/{token}) can view its prospects (contact details masked). Creates or re-enables the same token. List owner or admin only. Also the way to copy a list into ANOTHER Max workspace: the user opens the link while signed into that workspace and clicks Import.

create_prospect_profile_hook

Create a recurring watcher on a prospect (scrapecreators social posts, fullenrich contact refresh, or claire research). Each scheduled run may charge credits. Results land in list_prospect_profile_activities.

create_prospect_share_link

PUBLISHES the prospect publicly: anyone with the link (/share/{token}) can view it (contact details masked). Creates or re-enables the same token. Owner or admin only.

create_sales_catalog_field

Define a custom catalog field (max 50): key, label, type text|number|boolean|date|select, kind product|service|both, options (required for select only). Returns {data: Field}.

create_sales_catalog_item

Create a catalog product/service: name, kind; optional description, status draft|active|archived (default draft; only active can go on deals), unit_price+currency (both or neither), unit_label, attributes. Returns {data: Offering}.

create_saved_view

Save a named view (filters, sorting, columns, page size) on a list surface; appended as the last tab. 409 code name_taken on a duplicate name. Returns {data: SavedView}.

create_schedule_preset

Save a scheduling_config under a name so later campaigns can reuse it. Names are unique per workspace. Set is_default to pre-fill it on new campaigns. Applying a preset copies it — later edits never retime a running campaign.

crm_assign_prospects

Assign prospects to HubSpot owners using agent_settings.assignment_rules (or assignment_rules_override). First matching rule wins; no match → owner_id null, reason 'no rule matched', priority 'low'. Priority otherwise derives from prospect.score (>=75 high, 50–74 med, <50 low) else 'med'. Returns { assignments: [{ id|email, owner_id, owner_name, owner_email, reasoning, priority }] }.

crm_detect_forecast_changes

Compare current open HubSpot deals against the workspace's deal snapshot from window_days ago (read from max-agent's crm_deal_snapshots via GET /api/v1/crm/deal-snapshots). Flags amount changes (abs delta pct > threshold), stage moves (forward/backward via pipeline displayOrder), close-date slips (> threshold days), new deals since last snapshot, and deals that disappeared. Returns { window_days, baseline_iso, current_iso, changes:[{ deal_id, dealname, owner_id, owner_name, amount, prior_amount, amount_delta_pct, stage, prior_stage, stage_movement, close_date, prior_close_date, close_date_slip_days, flag_reasons[] }] }.

crm_export_import_csv

Build a HubSpot-import CSV (base64-encoded) from prospects. When dedup_against_hubspot (default true), drops prospects whose email already exists in HubSpot (concurrency <=5). Columns: Email, First Name, Last Name, Job Title, Company, Company Domain, Country, Industry, Number of Employees [, HubSpot Owner ID when include_assignment]. Returns { csv_base64, row_count, deduped_count, deduped:[{ email, existing_id }] }.

crm_get_contact

Fetch a single CRM contact by email (the dedup identity). Returns {data: contact} or {data: null} if not found.

crm_get_deal

Fetch a single HubSpot deal by id, including its full properties and associated company/contact ids. Returns null if not found.

crm_list_activities

List HubSpot engagements (call/email/meeting/note/task) with optional filters (deal, contact, owner, types, since). Per-type queries are merged sorted by timestamp desc. Returns id, type, timestamp, ownerId, dealId, contactId, subject, body.

crm_list_deals

List deals from HubSpot with optional filters (stage, owner, pipeline, amount range, close-date range, modified-after). Returns id, dealname, amount, ownerId, stage, pipeline, closeDate, lastModified, lastActivityDate, nextStep, associated company/contact ids.

crm_list_owners

List HubSpot owners (sales reps) for the workspace. Returns id, email, firstName, lastName, teams. Use to map deals/assignments to people.

crm_list_pipeline_stages

List deal pipeline stages (optionally scoped to one pipeline). Returns id, label, displayOrder, pipelineId, isWonStage, isLostStage.

crm_pipeline_risk_scan

Scan open HubSpot deals for risk: days inactive, days-to-close, missing fields (amount/owner/next_step/last_activity), close-date slipping, and high-value-low-activity. Computes a transparent weighted risk_score (0–100) and a PRIVATE suggested nudge draft to the owner (never sent). Uses agent_settings.risk_thresholds. Returns { scanned_count, flagged:[...] }.

crm_score_prospects

Score prospects 0–100 against the workspace ICP rules (agent_settings.icp_rules): country 25, industry 25, employee-in-range 20, any title keyword 30. With no rules configured, every prospect scores 50 (reason no_icp_rules_configured). Returns { scored: [{ id|email, score, matched[], missed[] }] }.

crm_search_contacts

Search the connected CRM (HubSpot) for contacts by free text (name, email, company). Returns {data: contacts[]}. Use before creating a contact to check if one already exists.

crm_status

Report whether HubSpot is connected for this workspace. Returns { connected: bool, provider, connections: [{ provider, portal_id, connected_at, last_refresh_at }] }.

crm_upsert_company

Create-or-update a company in the connected CRM, matched by domain — never creates a duplicate. Requires a read + write HubSpot connection.

crm_upsert_contact

Create-or-update a contact in the connected CRM, matched by email — never creates a duplicate. Use when the user asks to add or update a contact in HubSpot. Requires a read + write HubSpot connection.

crm_weekly_brief_compose

Compose a structured weekly sales brief from last week's activities, current open deals, the pipeline risk scan, and per-rep aggregates. Pure data (no writes). Returns { week_ending, last_week_summary, this_week_priorities, stale_deals, deals_without_next_step, top_risks, per_rep_questions, suggested_bj_notes, action_items }. Pass the result to notion_publish_weekly_brief to draft it in Notion.

decline_meeting

Reject a pending Cal.com booking request by meeting_id, with an optional reason. Irreversible; Cal.com notifies the attendee. Returns {data: meeting row} with status 'rejected'; 409 if the meeting is not pending.

delete_calendar_event

Delete an event from a synced Google/Outlook calendar by event_id + account_id. Irreversible; the provider may notify attendees. Returns {success: true}; 404 if the event is not found.

delete_campaign

Permanently delete a campaign and all its workflow executions. Prefer archive for soft removal.

delete_deal

Permanently delete a deal, its line items and attached files. Irreversible. Fails (500) if documents are linked to it. Returns {success: true}.

delete_deal_attachment

Permanently delete a file attached to a deal. Irreversible. Returns {success: true}.

delete_deal_pipeline

Permanently delete an EMPTY deal pipeline; 409 pipeline_in_use if it holds deals (archive it instead). The last pipeline can't be deleted. Returns {success: true}.

delete_deal_stage

Delete a custom deal stage (default stages can't be). If it holds deals, pass reassignTo (a stage in the same pipeline) or it 409s reassign_required. Returns {success: true}.

delete_deal_stage_rule

Delete a deal stage entry rule. Returns {success: true}.

delete_icp

Permanently delete an ICP and its record links (searches it produced are kept). Prefer update_icp status=archived. Returns {data: {id}}.

delete_organization

Delete an organization. Linked prospects get organization_id = null.

delete_prospect

Delete a prospect permanently.

delete_prospect_list

Delete a prospect list (prospects themselves are NOT deleted).

delete_prospect_profile_hook

Delete a profile hook permanently.

delete_saved_view

Permanently delete a saved view (creator or signed-in admin only). Records are untouched. Returns {data: {id}}.

delete_schedule_preset

Delete a saved schedule. Campaigns keep their own copy, so this never changes how an existing campaign sends.

detach_campaign_audience_list

Detach a prospect list from a campaign. People it already enrolled stay in — use remove_campaign_audience_prospects to stop them.

disable_trigger

Disable an intent trigger (sets active=false) so it stops re-polling. Returns the updated {data: IntentTrigger}, or a 404 error if the trigger is not in this workspace.

disconnect_account

Disconnect a LinkedIn or email account from the workspace. Use hosted_auth_link to reconnect.

disconnect_data_supplier

Revoke the workspace's stored key for a data supplier; searches stop using it until a human reconnects it. Returns {data: {provider, connected: false}}.

disconnect_synced_calendar_account

Disconnect a synced Google/Outlook calendar account by account_id (any member's, not only yours) and stop syncing it. Destructive: only the owner can reconnect it, by signing in again in the app. Returns {success: true}.

dismiss_duplicate_pair

Mark a duplicate pair as not-a-duplicate so it leaves the pending queue. Records are untouched. Returns {success: true}.

duplicate_campaign

Copy a campaign into a new draft (workflow, scheduling, exclusions, lists, accounts). Run history, enrolled people and sharing are not copied. Returns { campaign }.

enrich_contact_details

Find emails/phones (optionally LinkedIn URLs) for prospect_ids or a whole list_id via FullEnrich (default) or Explorium; results are written onto the prospects. CHARGES CREDITS (402 if insufficient) — run preview_enrichment first for the cost. Async: returns 202 {job_id, job_ids, status, total}; poll get_contact_enrichment_job.

enrich_organization

Run Claire deep-research on an organization and save the result onto the record. SYNCHRONOUS — waits for Claire (may take 30-180s) and returns {status} ('complete' with the research, 'skipped' if the org has no name, or 'busy' if another enrichment is already running). Counts against the workspace's daily enrichment quota; returns a 429 quota error when exhausted. Set force=true to re-enrich an already-complete record.

enrich_prospect

Run Claire deep-research on a prospect and save the result onto the record. SYNCHRONOUS — waits for Claire (may take 30-180s) and returns {status} ('complete' with the research, 'skipped' if the prospect has no name, or 'busy' if another enrichment is already running). Counts against the workspace's daily enrichment quota; returns a 429 quota error when exhausted. Set force=true to re-enrich an already-complete record. Call this BEFORE crafting personalized outreach.

enrich_prospect_with_claire

Resolve one prospect through Claire and fill missing/wrong fields (conflicts saved as alternates). CHARGES CREDITS on every lookup, even a miss; a complete record returns skipped:true free. 402 = insufficient credits. Synchronous, up to ~2 min.

explorium_add_more

Append more leads to an existing Explorium list (async). Re-runs the saved search for additional results. Poll the list (or use wait_for_prospect_list) for progress.

explorium_create_company_list

Create an Explorium-backed company (organization) list (async). Prefer auto_create_organization_list, which tries GetLeads first; use this to pin Explorium for revenue, age, tech-stack or intent filters. Business search → enrichment → ingestion. Returns a pending list; poll with wait_for_prospect_list.

explorium_create_list

SECOND CHOICE after getleads_create_list: create an Explorium-backed prospect (people) list (async). Use when GetLeads can't express the filters (buyer intent, departments, revenue, website keywords, enrichments) or returned nothing. People search → enrichment → ingestion; ~100× GetLeads' cost. Returns a pending list; poll with wait_for_prospect_list.

generate_icp

Draft an ICP with Max from a free-text brief (or refine icp_id). CHARGES workspace credits; slow (up to ~90s). Returns an UNSAVED {data: {draft, model, truncated}} — save it with create_icp/update_icp and source='max'.

generate_message_preview

Use AI to generate a personalized message for a prospect. Charges credits. Specify channel and prompt.

generate_workflow

Use AI to generate a campaign workflow from natural language. Charges credits. Provide a prompt or structured fields.

generate_workspace_intel

Have Max scan the workspace's People and Organization cards and write a workspace intel report, OVERWRITING the saved one. CHARGES workspace credits; slow (up to ~2 min). 422 if there are no cards. Returns {data: WorkspaceIntel}.

get_account

Get full details of a connected account — provider, channel, config, sync status.

get_account_rate_limits

Get daily/weekly sending limits and current usage for a specific account.

get_agent_session_messages

Read one of the caller's Max chat threads, oldest message first (first 500). Returns {data: {session, messages}}.

get_analytics_overview

Workspace analytics for a period, optionally filtered by campaign_ids/account_ids: totals and rates per channel (email, LinkedIn, WhatsApp, mail, meetings), by_campaign, by_account, prospect_lists, deals, crew, signals, funnel, previous-period totals (when from is set) and a daily timeseries. Large payload — narrow the period.

get_availability

Fetch open booking slots for an event type, grouped by date. event_type_id defaults to the connection's default event type; start defaults to now and end to now + 14 days; time_zone is an optional IANA string to localize slots. Returns {data: {eventTypeId, slotsByDate: {: [{start, end?}]}}}. Fails with 409 if no calendar is connected, or 400 if no event type id is available.

get_campaign

Get full details of a campaign by ID — workflow, scheduling, accounts, prospect lists, stats.

get_campaign_ab_tests

Every email step testing 2+ variants: weights, live traffic share, per-variant sent/open/click/reply/bounce rates and a verdict (collecting/inconclusive/winner with confidence). Empty tests[] when none run.

get_campaign_audience

Lists the campaign draws from (included/excluded, live member count, pending_count not yet enrolled) plus a rollup: in_campaign, active, finished, removed, manual, pending_from_lists. Also says whether the audience is editable and enrolls immediately.

get_campaign_engagement_summary

Engagement summary for a campaign: open/click/reply/bounce rates plus per-link click detail (top links, distinct URLs clicked).

get_campaign_feed

Most recent workflow steps executed in a campaign, newest first: node, action_type, status, error_message, prospect. limit default 20, max 100.

get_campaign_launch_preflight

Before launch: how many people in the audience at least one sequence step can reach. Returns { audience, reachable, unreachable, required_channels, segments } (segments keyed by channel combo, e.g. 'email+linkedin').

get_campaign_lead_analytics

Per-prospect breakdown — where each lead is in the workflow and message event history.

get_campaign_memory

Read Max's durable memory for a campaign (ICP, decisions, notes). Recall this when working on one of several simultaneous campaigns so you keep them straight.

get_campaign_node_run_counts

Map of workflow node ID → execution count. Useful for funnel visualization.

get_campaign_share_link

Read a campaign's public share link: { data: { token, enabled, view_count, ... } | null }. Public URL is /share/. Owner or workspace admin only.

get_campaign_stats

Aggregate performance stats — email open/reply rates, LinkedIn connection/reply rates, execution counts.

get_channel_sync_rules

Get one account's Unibox history-import rules. No rules = import everything.

get_chat

Get full details of a single Unibox chat/conversation thread.

get_circuit_status

Inspect the circuit-breaker state for each upstream host the MCP server has called. Shows whether requests are being fast-failed (state=open), probing (half-open), or flowing normally (closed).

get_contact_enrichment_job

Status of a contact-enrichment job: {job_id, status (pending|processing|completed|failed), total, enriched_count, error_message}. Poll until completed or failed, then re-read the prospects.

get_current_workspace

Return the Max workspace this connection reads and writes: {data: {workspace_id, workspace_name, auth_method, scopes}}. A Max API key reaches exactly ONE workspace; no tool can act in another. Check this before writing when the user names a workspace. If it differs: to copy a prospect list there, use create_prospect_list_share_link and have the user open the link while signed into the target workspace and click Import; to work there directly, the user connects that workspace's Max MCP key (Settings → API keys in that workspace).

get_dashboard_kpis

Workspace-wide aggregate stats — execution counts, email/LinkedIn rates, completion percentage.

get_data_quality_settings

Read the workspace's duplicate auto-merge policy. Returns {data: {auto_merge_enabled, auto_merge_threshold_percent}}.

get_deal

Get one native deal by deal_id with its organization and linked contacts (each omitted if the key lacks organizations:read / prospects:read). Returns {data: Deal}.

get_deal_board_totals

Per-stage totals for one deal pipeline, optionally filtered by status/owner_id/organization_id/search. Returns {data: {: {count, sums: [{currency, amount, weighted}]}}}; weighted = amount × probability.

get_email_tracking_events

Raw per-event email tracking rows for a prospect (opens, clicks, replies, bounces) with url/ip/user_agent detail. Newest first. Optionally filter by event_types.

get_email_verification_job

Status of an email-verification job: {job_id, status (pending|processing|completed|failed), total, error_message}. Poll until completed, then read verdicts from the prospects.

get_enrichment_credits

Return the workspace's daily enrichment quota usage: {cap, used_today, remaining}. Check this before a large bulk enrichment to confirm there's headroom.

get_enrichment_status

Check the enrichment state of a single prospect or organization. Provide exactly one of prospect_id or organization_id. Returns {enrichment_status, enrichment_updated_at, has_research}.

get_entity_analytics

360° analytics for one person (prospect) or organization over a period: touch totals per channel, meetings, by_campaign enrollment, linked deals, by_contact (organizations), daily timeseries and comparison totals. 404 if not in this workspace.

get_icp

Get one ICP by id with its criteria, profile and stats. Returns {data: Icp}.

get_inbox_autopilot_status

Return the workspace's current inbox autopilot setting: {enabled, mode ('auto_safe'|'draft_all'|'off'), daily_cap}. Use this to confirm whether autopilot is active and how it is configured before changing it or reviewing drafts.

get_inbox_placement

Get one inbox placement check: {check, result} with placement per provider and per seed inbox once completed (result null until then).

get_link_click_details

Link clicks for a campaign grouped by url, with total click counts and unique-prospect counts. Sorted by clicks desc.

get_mailpool_pricing

Monthly price per done-for-you mailbox (USD and credits) for Google and Microsoft, and whether purchasing is enabled.

get_organization

Get full details of an organization — domain, industry, employee count, funding, social URLs.

get_organization_geo_points

The workspace's organizations geocoded from city/country to lat/lng: { points: [{ id, name, city, country, lat, lng, precision }], capped }. Ungeocodable ones are omitted; capped=true means the list was truncated.

get_organization_geo_stats

Geographic distribution of the workspace's organizations: { total, located, byCountry: [{ country, count }], byCity: [{ city, country, count }] }.

get_organization_share_link

Read an organization's public share link: { data: { token, enabled, view_count, ... } | null }. Public URL is /share/. Owner or workspace admin only.

get_people_share_link

Get the public share link of the workspace's whole People database {token, enabled, view_count} or null. Admin only.

get_prospect

Get full profile of a prospect — name, title, company, LinkedIn, email, location, enrichment data.

get_prospect_campaign_activity

Chronological log of message events for a prospect across all campaigns (newest first).

get_prospect_engagement_timeline

Chronological email engagement timeline for a prospect (oldest first) — every open, click, reply, and bounce.

get_prospect_list

Get full details of a prospect list by ID — status, search config, result counts, timestamps.

get_prospect_list_share_link

Get a list's public share link {token, enabled, view_count} or null. List owner or admin only.

get_prospect_qualification

Qualification derived from the prospect's latest confirmed meeting transcript. Returns {state: available|needs_confirmation|no_meeting, meeting, qualification}. API keys need prospects:read AND workspace:read.

get_prospect_share_link

Get a prospect's public share link {token, enabled, view_count} or null. Owner or admin only.

get_sales_workspace

Read-only map of the sales setup (lists, campaigns, signals, people/deal pipelines and stages, stage rules, meetings) as {nodes, edges, notices, updatedAt}. limit caps each source (1-100, default 50).

get_saved_view

Get one saved view by id. Returns {data: SavedView}.

get_signal_history

Return the detected SignalEvent rows for a single trigger — each event records whether the poll found changes, a summary, and the raw scrape. Returns {data: SignalEvent[]}.

get_signal_proposal

Fetch a single signal proposal by id, including its full recommendation (campaign name/description, workflow_config, target_prospect_ids, estimated contacts/credits, matched ICP, and entity). Returns {data: SignalProposal}, or a 404 error if not found.

get_team_calendar_availability

Per-member free/busy from the workspace's synced Google/Outlook calendars (not Cal.com); books nothing. Free time counts only inside working hours (start_hour/end_hour/days/time_zone, default 09-18 Mon-Fri UTC); is_available = longest free run >= min_free_minutes. Returns {data: {window, members: [{user_id, name, has_calendar, stale, free_minutes, busy_blocks, next_free_at, is_available, ...}]}}.

get_unibox_message

Get one Unibox message's full body as plain text: {id, chat_id, subject, text}. Private messages return 404.

get_unibox_sync_progress

Live state of the Unibox history import: per-account phase and counters plus a summary. Cheap; poll while sync_unibox runs.

get_upcoming_meetings

List upcoming meetings (excluding cancelled/rejected) ordered by start time ascending. from defaults to now and to defaults to now + 30 days (both ISO8601). Returns {data: meeting row[]} (status one of pending|scheduled|rescheduled|completed|no_show; pending = awaiting confirm_meeting / decline_meeting).

get_warmup_deliverability

Warm-up health of every done-for-you mailbox, read live from Mailpool: status, health score, inbox rate, landed-inbox/spam totals and a daily series.

get_warmup_pricing

Warm-up price per mailbox (daily credits/USD, monthly USD) and whether purchasing is enabled.

get_workspace_agents

Read the workspace's agent configuration (soul, system prompt overrides, knowledge, skill switches per agent) plus shipped baselines and the caller's access. Read-only via API key. Returns {data: {config, access, baselines}}.

get_workspace_profile

Fetch workspace profile settings (company info) for the authenticated workspace via DigitalCrew API. Uses the MCP connection Authorization: Bearer token when set.

get_workspace_wallet

Read the workspace's token balances: pooled wallet, owner balance, spendable total and caller contribution. Returns {data: {wallet_balance, owner_balance, spendable, …}, billingEnabled}.

getleads_add_more

Append more contacts to a COMPLETED GetLeads list (async), re-running its saved filters from the next offset. Charges credits per contact returned. Poll with wait_for_prospect_list.

getleads_create_list

FIRST CHOICE for sourcing new people: create a GetLeads-backed prospect list (async). Needs at least one targeting filter (job_titles, seniority, countries, industries or domains). Returns a pending list; poll it with wait_for_prospect_list. Charges credits per contact returned. Use Explorium only for buyer intent, departments, revenue or keywords, or when GetLeads returns nothing.

hosted_auth_link

Generate a short-lived URL for the user to connect a LinkedIn or email account via Unipile hosted auth.

import_prospect_list_csv

Create a new prospect list and import prospects in one call. Each row needs an email (for dedup).

launch_campaign

Launch a draft campaign — transitions draft → active and creates workflow executions for each prospect.

link_icp

Mark a deal, organization or prospect as matching an ICP, with optional fit_score (0-100) and rationale. Upserts: re-linking updates the existing link. Returns {data: IcpLink}.

linkedin_cancel_invitation

Cancel/withdraw a sent LinkedIn invitation by its invitation_id (from list_invitations_sent).

linkedin_comment_on_post

Comment on a LinkedIn post.

linkedin_create_post

Create a LinkedIn post from the connected account.

linkedin_find_profile

Find a LinkedIn profile by name, company and/or title. Searches LinkedIn directly — always use this before any invitation or message. If multiple people share the name, returns candidates with ambiguous:true; show them to the user and ask which one. Never guess a slug or proceed when ambiguous.

linkedin_get_all_messages

Get all recent LinkedIn messages across all conversations.

linkedin_get_company_profile

Get a LinkedIn company profile by its identifier or slug.

linkedin_get_conversation_messages

Get messages in a specific LinkedIn conversation.

linkedin_get_own_profile

Get the profile of the connected LinkedIn account. Useful to confirm the account is active.

linkedin_get_profile

Get a full LinkedIn profile by slug (public identifier). Returns provider_id and profile data.

linkedin_get_user_posts

Get recent posts by a LinkedIn user.

linkedin_list_connections

List first-degree LinkedIn connections of the connected account.

linkedin_list_conversations

List LinkedIn conversations (inbox).

linkedin_list_invitations_received

List pending LinkedIn invitations received from others.

linkedin_list_invitations_sent

List pending LinkedIn invitations you have sent.

linkedin_react_to_post

React to a LinkedIn post.

linkedin_reply_in_chat

Reply in an existing LinkedIn conversation.

linkedin_search_people

Search LinkedIn for people by keywords.

linkedin_send_invitation

Send a LinkedIn connection request. ALWAYS call find_profile first to get provider_id.

linkedin_send_message

Send a LinkedIn direct message to start a new conversation. Requires existing connection or InMail credits.

list_account_shares

List the other workspaces a connected account is shared with (they see its live conversations). Returns share rows with the campaign/direct conversation flags.

list_accounts

List all connected LinkedIn and email accounts — name, email, status, daily limits.

list_agent_sessions

List the caller's own Max chat threads (API key: its owner's), most recent first, for one surface (default max_chat). Returns {data: AgentSession[]}.

list_campaign_audience_prospects

Paginated people in a campaign with enrollment status, source (list/manual) and workflow execution status. Filter by search, enrollment_status, source. Returns { data, count, page, pageSize }.

list_campaign_conversations

Newest-first feed of every Unibox message the campaign sent/received (chat_id, direction, subject, preview, status) merged with its physical letters (delivery status). Returns { data: { items, counts } }.

list_campaigns

List all outreach campaigns. Filter by status, search by name, paginate and sort.

list_chat_messages

Get all messages in a conversation — body, direction (in/out), timestamp, status.

list_chats

List LinkedIn and email conversations — filter by channel, prospect, account, or archived status.

list_conversation_analytics

Conversation-intelligence rollup of analyzed meetings in a period: {data: {totals (analyzedConversations, averageScore, averageInternalTalkPct, objectionRatePct, highRiskDeals), forecast, benchmarks per rep, trackerTrends, dealRisks, coachingLibrary}}.

list_crew_rates

List hourly rates and commission for the workspace default, members and digital workers. Returns {data: [{subject_type, subject_id, label, currency, hourly_rate, commission_pct, default_action_minutes, weekly_capacity_hours}]}.

list_custom_fields

List the workspace's custom field definitions, optionally for one entity_type (prospect, organization, deal). Returns {data: [{id, entity_type, key, label, field_type, options, is_required, default_value, position, is_archived}]}.

list_data_suppliers

List the bring-your-own-key data suppliers (getleads, explorium, apollo) with enabled flag, status (active/revoked/error) and saved default config. Never returns keys. A disconnected supplier can still show connected=true — trust status. Returns {data: DataSupplier[]}.

list_deal_attachments

List files attached to a deal — metadata only (file_name, mime_type, size_bytes, created_at, derivation status); no file contents. Returns {data: Attachment[]}.

list_deal_line_items

List a deal's product/service line items (snapshots, including removed ones with removed_at set). Returns {data: LineItem[]}.

list_deal_pipelines

List deal pipelines with their ordered stages (id, label, type open/won/lost, win_probability, rule_count). Seeds the default pipeline on first use. Returns {data: Pipeline[]}.

list_deal_stage_events

A deal's stage-change history, newest first. Returns {data: [{from_stage_id, to_stage_id, amount_at_change, changed_by, changed_at}]}.

list_deal_stage_rules

List a deal stage's entry-automation rules (run whenever a deal enters the stage). Returns {data: Rule[]}.

list_deals

List deals in Max's native pipeline (not HubSpot — that is crm_*). Filter by pipeline_id, stage_id, status, owner_id, organization_id, prospect_id, search or close-date window; paginate/sort. Returns {data: Deal[], count, page, pageSize}.

list_digital_workers

List the workspace's digital workers (AI crew members) with status, role, access mode and permissions. Returns {data: DigitalWorker[]}.

list_duplicate_records

List pending duplicate pairs for prospects (default) or organizations, each with match_type, confidence and a summary of both records. Returns {data: Pair[], counts} (pending counts per match type). Merging is a human action in the app.

list_failed_requests

Inspect the dead-letter queue — write requests (POST/PATCH/DELETE) that exhausted all retries. Useful for forensics or manual replay. Backed by Redis if REDIS_URL is set, otherwise an in-memory ring buffer of up to 500 entries.

list_icp_links

List the deals, organizations and prospects an ICP claims. Returns {data: IcpLink[]} (entity_type, entity_id, entity_label, fit_score, rationale, linked_by).

list_icps

List the workspace's Ideal Customer Profiles (default first). Filter by status (default active) or name search. Returns {data: Icp[]} with criteria, profile and stats (linked deals/organizations/prospects, searches run).

list_icps_for_record

Reverse lookup: which ICPs claim this deal, organization or prospect. Returns {data: IcpLink[]} including icp_name.

list_inbox_drafts

List the autopilot-generated reply drafts awaiting review (status='draft') for the workspace, newest first. Returns {data: InboxAutopilotAction[]}, each row including intent, sentiment, confidence, and the proposed reply_body. Review these before calling approve_inbox_draft or reject_inbox_draft.

list_inbox_placements

List inbox placement (spam) checks run on the workspace's done-for-you mailboxes, newest first: status, score, inbox/spam/promotions counts. results inlines the full result of the N latest completed checks.

list_intent_signals

List the workspace's intent triggers (optionally filtered by active state) so you can see what is being monitored and review recent signal activity. Returns {data: IntentTrigger[]}, each row including last_run_at and last_error. Use get_signal_history to drill into the detected events for a specific trigger.

list_mailpool_domains

List domains this workspace already bought through done-for-you setup, with Mailpool status, so new mailboxes can reuse them.

list_mailpool_orders

List the workspace's done-for-you email setup orders: domains, mailboxes, provisioning status and billing.

list_organizations

List all organizations/companies — search by name or domain, filter by industry/country.

list_prospect_campaigns

Campaigns a prospect is enrolled in: campaign name/status, enrollment status, source, added/removed dates, next scheduled step.

list_prospect_list_member_ids

IDs of every list member matching filters, unpaginated, for bulk actions. Returns {ids, count, truncated} (ids capped at limit).

list_prospect_list_members

List all prospects in a specific list — paginated, searchable, sortable.

list_prospect_list_organizations

List companies in an organization-type list (search_type=organizations). Paginated, searchable. Returns {data: Organization[], count}.

list_prospect_lists

List all prospect lists — name, status, result counts, and search criteria.

list_prospect_profile_activities

Stored social/profile activity timeline for a prospect (posts, contact changes, research found by profile hooks), newest first.

list_prospect_profile_hooks

Recurring watchers on a prospect (provider, source, frequency, active, last run status).

list_prospects

List prospects with rich filtering — search, status, org, titles, countries, industries, pagination, sorting.

list_sales_catalog_fields

List the custom catalog field definitions (key, label, type, kind, options) that catalog items' attributes use. Returns {data: Field[]}.

list_sales_catalog_items

Search the products/services catalog (30 per page) by name or kind. Returns {data: Offering[], count}.

list_saved_views

List one surface's saved views in tab order (workspace-shared plus your private ones). Returns {data: SavedView[]} with name, visibility, is_default, position, config.

list_schedule_presets

List the workspace's reusable sending schedules (timezone, available days, time windows). Check these before asking someone to spell out a schedule — copy the default one's scheduling_config into a new campaign.

list_signal_proposals

List the AI-generated campaign proposals produced from detected signals, optionally filtered by status (pending, approved, rejected, modified, launched, expired). An unknown status is ignored and all proposals are returned. Returns {data: SignalProposal[]}. Review pending proposals before approving them.

list_synced_calendar_accounts

List the workspace's connected Google/Outlook calendar accounts (synced via Unipile; separate from Cal.com). Returns {data: [{id, provider, externalAccountEmail, status, lastSyncedAt, syncIssue, needsReauth, scopeMissing, canReconnect}]}; id is the account_id the other synced-calendar tools take.

list_unibox_channels

List the accounts the Unibox imports (own + shared-in email, LinkedIn, WhatsApp) with message/contact stats, the last history-import job and each account's sync rules.

list_wallet_budgets

List per-member spending allowances on the workspace wallet. Returns {data: MemberBudget[]}.

list_wallet_consumption

Who spent how many workspace tokens, with their allowance, optionally since a timestamp. Returns {data: MemberConsumption[]}.

list_wallet_gifts

List token gifts this workspace gives to other workspaces (one-off and recurring). Returns {data: WorkspaceGrant[]}.

list_warmups

List the workspace's email warm-ups, the mailboxes eligible for warm-up (with a reason when not), and current pricing: {data, eligible, pricing}.

list_workspace_members

List human members and pending invites. Returns {data: [{id, user_id, name, email, role, custom_role, status, access_mode, is_admin, permissions, invited_at, joined_at}]}.

list_workspace_roles

List custom roles with their object/field permissions and assignment counts. Returns {data: CustomRole[]}.

lose_deal

Mark a deal lost with optional lost_reason: moves it to its pipeline's lost stage and runs that stage's entry rules. Returns {data: Deal}.

meetings

Read and annotate the workspace's meetings (meeting hub), and read or stop its Vexa recording bots. The workspace comes from your bearer token — prospect_id filters within it.

modify_proposal

Adjust a pending proposal WITHOUT launching it: pass modifications (titles, target_prospect_ids, campaign_name, campaign_description) to re-select prospects and regenerate the campaign workflow. The proposal stays pending so it can be reviewed and approved later. Returns the updated {data: SignalProposal}. Fails with 409 if the proposal is not pending, or 404 if not found.

move_deal

Move a deal to stage_id (any pipeline). Runs the target stage's entry rules (notify, assign owner, or enroll the primary contact in a campaign). A won stage needs a linked contact. Returns {data: Deal}.

notion_append_blocks

Append an array of Notion block JSON objects to an existing page (chunked into ≤100-block requests). Requires agent_settings.allow_notion_writes (default true). Returns { appended }.

notion_create_page

Create a new Notion page under a parent page, with an optional body of Notion block JSON. Requires agent_settings.allow_notion_writes (default true). Returns { id, url }.

notion_get_page

Fetch a Notion page object plus all of its child blocks (paginated). Returns { page, blocks }.

notion_publish_weekly_brief

Render a crm_weekly_brief_compose output as a DRAFT Notion page (H1 title + H2 section per part) under the workspace's Drafts/the assistant parent. Write-gated by agent_settings.allow_notion_writes. Defaults parent to agent_settings.notion_drafts_parent_id and template to agent_settings.notion_weekly_template_id. Returns { page_id, url, status:'draft', partial_success? }.

notion_search_pages

Search the connected Notion workspace for pages matching a free-text query. Returns [{ id, title, url }].

pause_campaign

Pause an active campaign — stops dequeueing new actions (in-flight calls finish).

pipeline_create_campaign_route

Route a campaign outcome (contacted/replied/bounced/opted_out) into a column: prospects are moved there automatically when it happens. One route per campaign+outcome (409 if taken). Returns {data: CampaignRoute}.

pipeline_create_canvas_draft

Start a change set based on current Production (empty, or duplicate_from another); add operations with pipeline_update_canvas_draft. Returns {data: ChangeSet} incl. revision and definition.base.

pipeline_create_link

Link two pipelines, or two columns (both stage ids) as a handoff; auto_move=true moves every prospect entering from_stage into to_stage. Returns {data: Link}.

pipeline_create_pipeline

Create a pipeline (max 12 per workspace); starter columns are seeded unless seed_stages=false. Returns {data: Pipeline}.

pipeline_create_stage

Add a column to a pipeline (workspace default when pipeline_id omitted; max 24 per pipeline). Returns {data: Stage}.

pipeline_create_stage_rule

Add an on-enter rule to a column: every prospect entering it gets rule_action (enroll in campaign, notify, assign, create deal, move, set field) — fires for real prospects once enabled. Cross-workspace move_stage needs a signed-in user, not an API key. Returns {data: StageRule}.

pipeline_delete_campaign_route

Delete a campaign outcome route. Returns {success}.

pipeline_delete_canvas_draft

Delete an unpublished change set. Returns an empty body (204) on success.

pipeline_delete_link

Delete a pipeline link (stops its auto_move handoff). Returns {success}.

pipeline_delete_pipeline

Permanently delete a non-default pipeline with its stages and links. If it holds prospects pass reassign_to, else 409 reassign_required. Returns {success}.

pipeline_delete_placement

Forget a canvas node's saved position so it is auto-laid-out. Layout only. Returns {success}.

pipeline_delete_stage

Permanently delete a custom column (system columns can't be deleted; archive instead). If it holds prospects pass reassign_to, else 409. Returns {success}.

pipeline_delete_stage_rule

Permanently delete a stage rule. Returns {success}.

pipeline_get_canvas

The whole journey graph in one read: pipelines with stages, prospect and rule counts, links, campaigns and their routes, stage automations, webhooks and their routes, deal pipelines. Returns {data: {...}}.

pipeline_get_canvas_draft_diff

Review a change set against current Production: additions, edits, removals, relocations, warnings, conflicts and drift. Returns {data: Diff}.

pipeline_get_pipeline

Get one pipeline with all its stages (archived included). Returns {data: Pipeline & {stages: Stage[]}}.

pipeline_get_prospect_journey

One prospect's stage-change trail across pipelines, oldest first. Returns {data: {current, entry, steps[], pipelines_visited[], truncated}}.

pipeline_list_campaign_routes

List campaign outcome routes (campaign outcome → column). Returns {data: CampaignRoute[]}.

pipeline_list_canvas_draft_publications

A change set's publication history (reason, actor, before/after fingerprints, operations). Returns {data: Publication[]}.

pipeline_list_canvas_drafts

List Production change sets (reviewed batches of pipeline edits) with status, revision and operations. Returns {data: ChangeSet[]}; 404 if change sets are disabled.

pipeline_list_links

List pipeline links: journey edges between pipelines, or column-to-column handoffs when both stage ids are set. Returns {data: Link[]}.

pipeline_list_pipelines

List the workspace's prospect pipelines (funnels); seeds the default one on first call. Returns {data: Pipeline[]}.

pipeline_list_placements

List saved journey-canvas positions of campaign / webhook / deal-pipeline nodes. Returns {data: Placement[]}.

pipeline_list_stage_rules

List a column's on-enter automation rules. Returns {data: StageRule[]} with id, action, config, is_enabled, position.

pipeline_list_stages

List pipeline columns (stages), optionally for one pipeline. Returns {data: Stage[]} with id, pipeline_id, key, label, type, position.

pipeline_preview_rule_assignment

Dry-run an assign stage rule: who it would assign now (or at at) and why, with each candidate's calendar availability. Changes nothing. Returns {data: {assignees, candidates, strategy, reason}}.

pipeline_publish_canvas_draft

Atomically apply a 'ready' change set to Production — immediately changes live routing and automation for real prospects (may remove columns/archive pipelines). 409 production_drift if Production moved (rebase first). Returns {data: {publication_id, status, fingerprint, revision}}.

pipeline_rebase_canvas_draft

Re-base a drifted change set onto current Production (new base fingerprint); review and mark ready again before publishing. Returns {data: ChangeSet}.

pipeline_reorder_stages

Set a new left-to-right column order. Returns {data: Stage[]} (every column).

pipeline_rollback_canvas_publication

Create a NEW draft change set that reverts a publication (422 if Production changed since). Nothing goes live until it is marked ready and published. Returns {data: ChangeSet}.

pipeline_set_placement

Save where a campaign / webhook / deal-pipeline node sits on the journey canvas (upsert by kind + ref_id). Layout only. Returns {data: Placement}.

pipeline_update_campaign_route

Point a campaign route at another column, or arm/disarm it. Returns {data: CampaignRoute}.

pipeline_update_canvas_draft

Save a change set's name, full definition (operations) or status. Flow: save definition → status 'ready' (validates; 409 production_drift / 422 invalid) → pipeline_publish_canvas_draft. Returns {data: ChangeSet} with the new revision.

pipeline_update_link

Relabel, re-point, pin/unpin columns or arm/disarm auto_move on a pipeline link. Returns {data: Link}.

pipeline_update_pipeline

Rename, recolor, reorder or archive a pipeline, make it the default (is_default=true), or set its canvas position. Returns {data: Pipeline}.

pipeline_update_stage

Rename, recolor, retype, move or archive a column. Returns {data: Stage}.

pipeline_update_stage_rule

Change a stage rule's action, config, enabled flag or order. Returns {data: StageRule}.

pipeline_validate_canvas_draft

Check a change set against current Production without saving anything. Returns {data: {valid, drifted, issues[]}}.

pipeline_webhook_create

Create an inbound webhook endpoint that turns posted JSON into prospects. Pass to_stage_id to seed a catch-all branch into that column (otherwise add branches with pipeline_webhook_route_create). Returns {data} with endpoint_url, plus secret for auth_mode hmac/token. The secret is shown ONLY in this response and cannot be read again: give it to the user to store in the sender; never log or repeat it.

pipeline_webhook_delete

Permanently delete an endpoint with its branches and delivery log; its URL stops accepting posts. Returns {data: {id}}.

pipeline_webhook_get

Get one inbound webhook endpoint by webhook_id, with its routing branches. Returns {data: Webhook & {routes}}.

pipeline_webhook_list

List the workspace's inbound lead-capture webhook endpoints, each with endpoint_url, auth settings, health counters and its routing branches. Returns {data: Webhook[]}. Never includes secrets.

pipeline_webhook_list_deliveries

Read an endpoint's delivery log, newest first: received payload, status, matched branches, prospect_id, error. Filter by status (e.g. unmatched); paginate with page/pageSize. Returns {data: Delivery[], count}.

pipeline_webhook_replay_delivery

Re-run a logged delivery's payload through the endpoint's CURRENT mapping and branches (e.g. to recover leads after fixing a filter). dry_run defaults to FALSE: it really creates/moves prospects and fires column automations. Returns {data: {delivery_id, replay_of, status, prospect_id, matched}}.

pipeline_webhook_rotate

Replace an endpoint's credentials; the old ones stop working immediately. target=secret (default) issues a new HMAC secret/token (optionally switching auth_mode to hmac|token) returned as secret. The secret is shown ONLY in this response and cannot be read again: give it to the user to store in the sender; never log or repeat it. target=url issues a new endpoint_url; every sender breaks until updated.

pipeline_webhook_route_create

Add a branch sending payloads that match filter (omit = catch-all) from webhook_id into column to_stage_id. Returns {data: Route}; 409 if the endpoint already routes into that column.

pipeline_webhook_route_delete

Permanently delete a routing branch; payloads it matched fall through to the remaining branches. Returns {data: {id}}.

pipeline_webhook_route_list

List routing branches (payload filter -> destination column) in evaluation order, for one webhook_id or the whole workspace. Returns {data: Route[]}.

pipeline_webhook_route_reorder

Set the evaluation order of one endpoint's branches (under first_match, order decides where a lead lands). Returns {data: Route[]} in the new order.

pipeline_webhook_route_update

Partially update a branch: to_stage_id, label, filter (replaced whole), position, is_enabled. Returns {data: Route}.

pipeline_webhook_test

Run a sample JSON payload through an endpoint's current mapping and branch filters. dry_run defaults to true (creates nobody); dry_run=false really creates/updates the prospect and fires the destination column's automations. Returns {data: {status, mapped, matched, prospect_id, suggested_mapping, sample_signature}}.

pipeline_webhook_update

Partially update an endpoint (name, auth, field_mapping, routing/dedupe mode, rate limit, is_enabled). Changing auth_mode to hmac/token issues new material (the old stops working) returned as secret. The secret is shown ONLY in this response and cannot be read again: give it to the user to store in the sender; never log or repeat it.

preview_enrichment

Free, read-only estimate for enrich_contact_details / verify_emails over prospect_ids or a list_id. Returns {coverage (with_email, with_phone, missing_contact, unverified_email...), providers [{provider, eligible, skipped, estimated_credits, available}], balance}.

preview_organization_search

Run a small, unsaved company search (1–25 rows) to check targeting before building a list. Tries GetLeads first, then Explorium. Billed like any provider call. Returns {data: companies[], provider, attempts, dropped_filters}.

propose_times

Return the n soonest available slots as a flat list — handy for offering a prospect a few concrete times. count is 1-50 (default 3); event_type_id defaults to the connection's default event type; time_zone is an optional IANA string. Returns {data: {eventTypeId, slots: [{start, end?}]}}. Fails with 409 if no calendar is connected.

prospect_list_meetings

List the meetings involving one prospect, newest first — the prospect meeting feed. Same filters and shape as the meetings group's list action, with prospect_id required. Returns {data: MeetingSessionSummaryDto[], nextCursor}. Paginated: echo nextCursor back as cursor; null means the last page. prospect_id filters within your authenticated workspace.

prospect_list_tasks

List the tasks about one prospect, newest first. Same filters and shape as the tasks group's list action, with prospect_id required. Returns {data: TaskDto[], nextCursor}. Paginated: echo nextCursor back as cursor; null means the last page. prospect_id filters within your authenticated workspace.

refresh_prospect_images

Re-fetch the prospect's photo and their company's logo. Returns {photo_updated, logo_updated, photo_url, logo_url, warnings}.

refresh_prospect_social_profiles

Recompute the prospect's social_profiles list from its row and enrichment data (no provider call). Returns the refreshed list.

reject_inbox_draft

Reject a drafted reply so it will not be sent, setting the action's status to 'rejected'. No message is sent. Returns the updated {data: InboxAutopilotAction}. Fails with 404 (draft not found) or 409 (action not in 'draft' status).

reject_proposal

Reject a pending proposal so it will not be launched. Returns the updated {data: SignalProposal (status 'rejected')}. Fails with 409 if the proposal is not pending.

remove_campaign_audience_prospects

Take people out of a campaign and stop any in-flight executions so they get no further outreach. Enrollment is kept as 'removed'; a later sync never re-adds them.

remove_deal_line_item

Remove a line item from an OPEN deal (soft-removed, kept in history). Returns {data: {id}}.

remove_deal_prospect

Unlink a contact (prospect_id) from a deal. A won deal must keep at least one contact. Returns {success: true}.

remove_prospects_from_list

Remove prospects from a prospect list by their UUIDs.

reorder_deal_stages

Reorder a deal pipeline's stages; ordered_ids lists every stage id in the new order. Returns {data: Stage[]}.

reschedule_meeting

Move a scheduled Cal.com meeting (meeting_id) to new_start (future ISO8601; check get_availability first), with an optional reason. Cal.com emails the attendee the new time. Returns {data: meeting row} with status 'rescheduled' and a new calcom_booking_uid; 409 if the meeting is not active or its event type forbids rescheduling.

restore_campaign

Restore an archived campaign back to draft status.

resume_campaign

Resume a paused campaign — transitions paused → active.

resume_warmup

MAY CHARGE THE WORKSPACE: undoes a pending cancellation (free), or pays a past-due warm-up's next day now and re-enables it. Confirm with the user first. 402 when credits are short.

revoke_campaign_share_link

Disable a campaign's public share link — anyone holding the URL loses access immediately. Owner or workspace admin only.

revoke_organization_share_link

Disable an organization's public share link — anyone holding the URL loses access immediately. Owner or workspace admin only.

revoke_people_share_link

Disable the People database public share link; the URL stops working. Admin only.

revoke_prospect_list_share_link

Disable a list's public share link; the URL stops working (re-enabling restores the same token).

revoke_prospect_share_link

Disable a prospect's public share link; the URL stops working (re-enabling restores the same token).

run_prospect_profile_hook

Run a profile hook immediately (synchronous, up to ~5 min). May charge credits for the provider work. Returns {status, activitiesWritten, summary}.

scan_duplicate_records

Rescan all workspace prospects and organizations for duplicates now (can be slow). Returns {data: {prospects_scanned, organizations_scanned, new_candidates}}; read pairs with list_duplicate_records.

search_mailpool_domains

Check availability and annual price of a domain name across TLDs, plus suggestions and mailbox pricing. Read-only; buys nothing.

search_prospect_lists

Preview filter results without creating a list — search by titles, countries, industries, employee count, etc.

search_workspace

Full-text search across people, organizations, deals, lists, campaigns, tasks and meeting notes. Returns {query, groups:[{type, total, hits:[{id, title, subtitle, meta, href}]}]}; entity kinds the key lacks scope for come back empty.

send_booking_link

Compose the rep's public Cal.com booking link so it can be shared with a prospect. Does NOT call Cal.com. Optionally pass event_type_id (defaults to the connection's default) and prospect_id for context. Returns {data: {url, bookingLink, username}}. Fails with 409 if no calendar is connected.

send_chat_message

Send a manual reply in an existing Unibox chat. Channel (email/LinkedIn) is inferred from the chat.

send_new_email

Compose and send a brand-new email to any recipient, outside any chat or campaign. Sends from the workspace's connected email account. Use send_chat_message instead to reply within an existing conversation.

set_channel_sync_rules

Replace an account's Unibox history-import rules with the given full set (max 20). A message is imported when any enabled rule matches; [] imports everything. Returns the saved rules.

set_inbox_autopilot

Set the workspace's inbox autopilot configuration. enabled is the master kill switch (false = do nothing). When enabled, the autopilot reads each inbound email reply, drafts a suggested reply in the rep's voice, and NOTIFIES the user to review/approve it — it NEVER auto-sends; a human approves every reply (via list_inbox_drafts + approve_inbox_draft). mode: 'off' suppresses entirely; 'auto_safe' and 'draft_all' both draft-and-notify (auto-send is disabled in v1). daily_cap is reserved for a future auto-send mode. Returns the saved {data: inboxAutopilot}.

simulate_account_connected

Fire a Unipile account-connected webhook event. Use to test the handler that creates/updates an account record when Unipile finishes connecting.

simulate_account_status

Fire a Unipile account-status webhook. Use to test status changes (OK, CREDENTIALS, ERROR, CONNECTING, STOPPED). Useful for verifying that disconnected accounts are flagged correctly.

simulate_email_tracking

Fire a Unipile mail_opened or mail_link_clicked tracking event. Pass label as 'execution_state_id:node_id' to link the event to a campaign execution and increment open/click counts.

simulate_linkedin_messaging

Fire a Unipile LinkedIn messaging event (message_received, message_read, message_delivered, etc.). Use to test reply detection and campaign execution advancement on LinkedIn.

simulate_new_email

Fire a Unipile mail_received webhook. Use to test inbound email handling — reply detection, chat thread creation, and campaign execution advancement.

simulate_new_relation

Fire a Unipile new_relation event (LinkedIn invitation accepted). Use to test that the connection record is updated and any waiting campaign executions are advanced.

social_cancel_invitation

Withdraw a pending invitation sent by the account (LinkedIn only).

social_comment

Publish a comment on a post, or a reply to one of its comments, as the account (public). Returns {comment_id}.

social_create_post

Publish a text post as the account (public). LinkedIn only here: Instagram posts need an image, which this tool can't upload. Returns {post_id}.

social_endorse_skill

Endorse one of a person's LinkedIn skills as the account (publicly visible). Returns {endorsed}.

social_follow

Follow a person or company as the account (publicly visible). LinkedIn returns {requested: true}; the follow itself is not confirmed.

social_get_post

Get one post: text, author, date and reaction/comment/repost counters.

social_handle_invitation

Accept or decline an invitation received by the account. Returns {status: ACCEPTED|DECLINED}.

social_inmail_balance

Remaining LinkedIn InMail credits of the account per product: {premium, recruiter, sales_navigator}.

social_invite

Send a connection invitation (LinkedIn) or follow request (Instagram) as the given account — goes out to the person. Returns {invitation_id}.

social_list_comments

List comments on a post, or replies to one comment. Paginated: {items, cursor}.

social_list_invitations_received

List invitations received by the account. Paginated: {items, cursor}.

social_list_invitations_sent

List pending invitations sent by the account. Paginated: {items, cursor}.

social_list_posts

List recent posts by a person or company: text, date, counters, share_url. Paginated: {items, cursor}.

social_list_reactions

List reactions on a post or comment, with who reacted. Paginated: {items, cursor}.

social_react

React to a post, or one of its comments, as the account (publicly visible).

social_relationship

Check whether the account is connected to a person (LinkedIn only): {status: connected|not_connected|unknown, network_distance}.

social_send_inmail

Send a LinkedIn InMail as the account — sends a message and spends one InMail credit of the chosen product (see social_inmail_balance). Returns {chat_id, message_id}; nulls mean accepted but delivery unconfirmed.

start_warmup

CHARGES THE WORKSPACE: buys email warm-up for each mailbox, billed the first day now and then daily until cancel_warmup. Confirm the mailboxes and price (get_warmup_pricing) with the user first. Returns {started, failed, tokens_charged}; 402 when credits are short, 422 when none started.

stop_campaign

Stop an active or paused campaign permanently — cannot be resumed.

suggest_campaign_ideas

Propose 3-8 distinct outbound campaign ideas for an audience. Charges credits (402 if insufficient); creates nothing. Returns {data: {ideas: [{title, description, instruction, play}]}} — pass an idea's instruction as generate_workflow's prompt.

suggest_chat_replies

Generate up to 3 ready-to-send reply drafts for a Unibox chat (nothing is sent). Charges 1 automation credit per call (402 when the balance is short). Returns {suggestions: [{label, intent, deal_target, rationale, text}], usedProspectCard}.

sync_accounts

Reconcile the workspace's connected accounts with Unipile: import accounts missing from Max, refresh statuses, remove duplicates, link done-for-you mailboxes. Safe to re-run; returns counts per pass and a message saying to run again when a large workspace was only partly synced.

sync_all_warmups

Refresh every live warm-up from Mailpool. Returns {data, unmanaged (warm-ups Mailpool runs that Max doesn't track), errors}.

sync_calendars_now

Pull the latest events from the synced Google/Outlook calendars now: every account, or only account_id. May take minutes; an account already mid-sync is skipped. Returns {data: {accounts, synced, needsReauth, failed, skipped, eventsUpserted, eventsCancelled, results: [{accountId, provider, status, error}]}}.

sync_campaign_audience

Enroll members added to the campaign's included lists since it started (minus excluded lists; removed people are never re-added). On an active/paused campaign they start the sequence immediately.

sync_mailpool_order

Refresh an order's domain/mailbox provisioning and DNS status from Mailpool, auto-connecting newly active mailboxes. Returns the order.

sync_unibox

Import message history from every connected account (or one account_id) into the Unibox. Long-running (up to ~5 min) and idempotent; returns partial:true when the time budget ran out — call again to continue. Track it with get_unibox_sync_progress.

sync_warmup

Refresh one warm-up's status and stats from Mailpool and return it.

tasks

Read tasks and propose new ones. Agents propose, humans dispose: you can create suggestions and drive accepted work forward, but only a human can approve or reject a suggestion. The workspace comes from your bearer token.

unlink_icp

Remove one ICP link by link_id (the record itself is untouched). Returns {data: {id}}.

update_account

Update account sender name, timezone, working hours, and email signature.

update_account_rate_limit

Update daily or weekly sending cap for a specific rate-limit row.

update_calendar_event

Patch an event on a synced Google/Outlook calendar by event_id + account_id; omitted fields are left unchanged. The provider may notify attendees. Returns {data: provider event}; 409 conflict if it was edited elsewhere, 401 reauth_required if the account must be reconnected.

update_campaign

Partial update of a campaign — name, description, workflow, lists, accounts, scheduling. Name and description can be changed at any status (including launched campaigns); all other fields require the campaign to be in 'draft' or 'stopped'.

update_campaign_ab_test

Apply one live traffic control to an email step's A/B test: pause/activate/promote a variant (needs variant_id), set_weights (needs weights), or reset. Takes effect on the next send, including already-enrolled prospects.

update_campaign_memory

Record/update Max's durable memory for a campaign. Pass a partial 'memory' object (top-level keys merge; send the full array to change decisions/notes). Use it to remember ICP, decisions, and progress per campaign.

update_chat

Update chat metadata — title, read state, archived status, prospect link.

update_data_supplier

Enable/disable a connected data supplier or replace its saved default search config. 404 if the provider is not connected. Returns {data: DataSupplier}.

update_deal

Partially update a deal (name, amount, currency, close_date, probability, owner_id, organization_id, description, custom_fields, lost_reason). Change stage with move_deal / win_deal / lose_deal. Returns {data: Deal}.

update_deal_pipeline

Rename, reposition, make default, or archive/restore a deal pipeline. Returns {data: Pipeline}.

update_deal_stage

Update a deal stage's label, color, type, win_probability or position. Changing type re-syncs its deals' status. Returns {data: Stage}.

update_deal_stage_rule

Update a deal stage rule's rule_action, config, is_enabled or position; config is re-validated against the action. Returns {data: Rule}.

update_icp

Patch an ICP: rename, archive, make default, or replace its criteria/profile. Omitted fields are untouched, but a sent criteria or profile object replaces that whole half. Returns {data: Icp}.

update_meeting_attendance

Mark (absent: true) or clear (absent: false) a guest's no-show on a Cal.com meeting that has already ended, by meeting_id and attendee_email. Returns the updated {data: meeting row}; 409 if the meeting has not ended, is pending/cancelled, or the email is not a recorded guest.

update_organization

Update an organization's fields (partial update).

update_prospect

Update a prospect's fields (partial update).

update_prospect_list

Update a prospect list (only list_name and status are editable).

update_prospect_profile_hook

Update a profile hook's source, label, custom_prompt, frequency, or active (false pauses it).

update_sales_catalog_item

REPLACE a catalog item: omitted optional fields reset to defaults, so send the full record plus expected_updated_at (its current updated_at; 409 if it changed). Returns {data: Offering}.

update_saved_view

Rename, reconfigure, reorder, share/unshare or make default a saved view. Only the view's creator (or a signed-in admin) may change it; else 403. Returns {data: SavedView}.

update_schedule_preset

Rename a saved schedule, replace its scheduling_config, or make it the workspace default. At least one field beyond the id is required.

update_warmup

Change a warm-up's daily target and ramp-up days. Returns the updated warm-up.

update_workspace_profile

Create or update workspace profile settings for the authenticated workspace via DigitalCrew API (PUT upsert). Uses the MCP connection Authorization: Bearer token when set.

verify_emails

Queue email verification (Bouncer) for prospect_ids or a whole list_id. CHARGES CREDITS (402 if insufficient). Async: returns 202 {job_id, job_ids, total}; a cron writes deliverable/risky/undeliverable/unknown onto each prospect's email_verification_status within ~5 min — poll get_email_verification_job.

wait_for_prospect_list

Poll a provider-built list (auto, GetLeads, Explorium, LinkedIn or Apollo) until its status becomes completed, failed, or cancelled — or the timeout elapses. Use after any *_create_list / *_add_more so the agent doesn't need to manage polling itself.

win_deal

Mark a deal won: moves it to its pipeline's won stage and runs that stage's entry rules. 400 deal_contact_required if no contact is linked (add_deal_prospect first). Returns {data: Deal}.

Variable

Required

Description

DIGITALCREW_API_BASE_URL

Yes

Base URL of the Digital Crew API (no trailing slash)

MCP_GATEWAY_SECRET

Yes (prod)

Shared secret; first-party callers send X-MCP-Gateway-Key on /mcp and /chat. External MCP clients use a workspace Max API key instead — Authorization: Bearer max_live_…, x-api-key: max_live_… or /mcp?key=max_live_… — on /mcp only

MCP_ADMIN_GATEWAY_KEY

No

Separate key required for admin tools when ENABLE_ADMIN_TOOLS=true

ALLOW_ENV_TOKEN_FALLBACK

No

Set true only for legacy scripts that cannot send per-request tokens

DIGITALCREW_API_TOKEN or DIGITALCREW_BEARER_TOKEN

No*

Used only when ALLOW_ENV_TOKEN_FALLBACK=true

ENABLE_ADMIN_TOOLS

No

Set true to expose dead-letter / circuit-breaker admin tools

ENABLE_WEBHOOK_SIMULATORS

No

Set true to expose webhook simulation tools (dev/staging only)

ENABLE_PURCHASE_TOOLS

No

Set true to expose the tools that spend real money: start_warmup, resume_warmup and create_mailpool_order (all need accounts:purchase). Off by default so a model cannot buy warm-up or mailboxes on its own initiative

CHAT_RATE_LIMIT_PER_MINUTE

No

Per-gateway-key chat limit (default 20)

CHAT_DAILY_REQUEST_CAP

No

Daily OpenRouter call cap per key (default 500)

REDIS_URL

No

Shared dead-letter queue and circuit-breaker state across instances