Margo
Server Details
Research business prospects with source evidence using your Margo account.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
Most tools target distinct lifecycle stages: capability discovery, usage checks, one-off search, status polling, cancellation, pipeline preparation, sampling, activation, reading, feedback, and updating. The main ambiguity is between one-off prospect search (`search_leads`) and pipeline sampling/discovery (`run_pipeline_sample`, `prepare_pipeline`), plus several read tools that differ by artifact (job status, sample results, durable feed). The descriptions clarify these boundaries, so confusion is limited.
All tool names use snake_case and follow a predictable verb_noun pattern such as `get_search_status`, `prepare_pipeline`, `read_pipeline_sample`, and `record_pipeline_feedback`. `get_margo_capabilities` is slightly branded but still fits the `get_*` convention. No mixed casing or inconsistent verb styles are present.
Thirteen tools is well within the expected range and each maps to a meaningful part of the paid research and recurring pipeline workflow. There is no obvious filler; the count supports the domain without becoming unwieldy.
The surface covers the core lifecycle: capability/usage discovery, one-off search, status polling, cancellation, pipeline drafting, sampling, activation, reading leads, feedback, and updating/pausing. Minor gaps include no explicit list/search-history operation for prior one-off searches and no archive/delete operation for pipelines. These are workaroundable or secondary to the main workflow.
Publisher details
- Operator
- Margo · Publisher source
- Operator website
- https://www.margoleads.io/ · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://www.margoleads.io/docs/mcp · Publisher source
- Privacy policy
- Not provided
- Trust center
- Unknown
- Restrictions
- Requires a Margo Professional or Business account with a verified email and an MCP client supporting remote Streamable HTTP. OAuth and source/account permissions apply. Research consumes existing credits within the explicit credit ceiling; connecting does not purchase credits or start a search. · Publisher source
Available Tools
13 toolsactivate_pipelineApprove recurring pipeline researchADestructiveInspect
Grant standing paid research authority only after the user reviews the exact saved structured requirements, preferences, exclusions, contact routes, source configurations and limits. A second sample is optional. objective text is context, not an automatically checked requirement. Activation binds that exact saved revision hash and enables recurring discovery within its limits. Requires pipelines:approve; delivery remains independently controlled.
Inputs: requestId (required), pipelineId (required), revisionId (required), revisionHash (required), +1 more.
cancel_searchCancel Margo searchADestructiveInspect
Cancel an owned search that is still queued or running. Already delivered research may remain billable. A terminal or unknown job returns an error.
Inputs: jobId (required).
get_margo_capabilitiesMargo research capabilitiesARead-onlyInspect
Read supported sources, country/city coverage, account availability, current credit tariffs, input contract and caveats. Does not run research or consume credits.
Inputs: no named parameters.
get_pipelinesList prospecting pipelinesBRead-onlyInspect
Read owned pipeline status, approved policy revisions, sample and recurring runs, budget and delivery switches. Does not run research or consume events.
Inputs: no named parameters.
get_search_statusMargo search resultsARead-onlyInspect
Poll an owned search and retrieve its results, source limitations, constraint coverage and terminal status. Poll the existing job; do not start another search. No new research credits.
Inputs: jobId (required).
get_usage_and_quotaMargo credits and usageADestructiveInspect
Refresh saved allowance-period accounting and read your current plan allowance and purchased credits before agreeing to a research search. Does not purchase credits.
Inputs: no named parameters.
prepare_pipelinePrepare a prospecting pipelineAIdempotentInspect
Create an account-owned draft for recurring Maps or LinkedIn discovery (one channel per pipeline) without running research, reserving credits or enabling delivery. objective is context only: explicitly encode requirements/preferences in icpContext.constraints, exclusions in constraints or icpContext.exclusions, and contact requirements in requiredContactRoutes. Read back and review the exact saved criteria, source configuration, schedule and limits with the user before activation. A second sample is optional.
Inputs: policy (required), requestId (required).
read_pipeline_leadsRead prospecting pipeline feedBRead-onlyInspect
Read the durable, replayable pipeline feed using its opaque cursor. Reads do not consume events or affect email/webhook delivery.
Inputs: pipelineId (required), limit, cursor.
read_pipeline_sampleReview a pipeline sampleARead-onlyInspect
Read the sample results and quality explanations for an owned source run before granting recurring authority.
Inputs: pipelineId (required), sourceRunId (required).
record_pipeline_feedbackRecord prospect feedbackADestructiveIdempotentInspect
Save an account-owned fit, accuracy, duplicate, pursuit or exclusion decision against a pipeline event. Exclusion, duplicate or not-relevant decisions suppress the prospect and pause associated monitoring; inaccurate or stale feedback changes review state. Reuse requestId when retrying one feedback submission.
Inputs: feedback (required), requestId (required), pipelineId (required).
run_pipeline_sampleRun a bounded pipeline sampleADestructiveIdempotentInspect
Prepare a fresh sample of at most five prospects from one selected pipeline source. The first call returns a quote without spending. To run it, repeat with the same requestId and the exact approvedMaxCredits after the user agrees. A sample approval is one-time and does not authorize recurring research.
Inputs: source (required), requestId (required), pipelineId (required), revisionId (required), +2 more.
search_leadsResearch prospects with MargoADestructiveIdempotentInspect
Create or resume one durable prospect search. Consumes Margo credits: check capabilities and usage and agree the cost with the user first. requestId must be unique per intended search and reused on retries; maxCredits is the agreed maximum. Returns a jobId for get_search_status. Country targeting for LinkedIn/Shopify; Maps supports city. Missing contacts and partial/empty results are possible.
Inputs: country (required), requestId (required), maxCredits (required), city, +14 more.
update_pipelineUpdate a prospecting pipelineADestructiveInspect
Pause or resume paid research and independently control email/webhook delivery to configured external destinations, or create a new immutable policy revision. Pausing can cancel pending research and queued deliveries. Preserve the full saved structured requirements, exclusions and contact routes when changing a policy; objective is context and is not parsed into criteria. Read back the exact saved revision for user review. Changing the channel, criteria or increasing limits requires approval of the exact new revision. A second sample is optional.
Inputs: pipelineId (required), policy, controls.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm37 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.