Crawdar Business Research
Server Details
Evidence-backed public business research for agents with compact, pageable output.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 21 tools
Most tools have clearly distinct resources and actions, and descriptions explicitly route between synchronous search, durable lead-search jobs, review scanning, and workspace research. The main ambiguity is between research_businesses, search_businesses, and start_lead_search, plus some overlap between scan_review_pain_points and research_opportunity_workspace.
The set uses consistent snake_case and predominantly follows a verb_noun pattern such as create_opportunity_workspace, get_lead_search, and cancel_lead_search. Minor deviations appear in shorter verb-only names like explain_crawdar, research_businesses, and sandbox_businesses, but the convention remains readable and predictable.
With 21 tools, the surface is heavy for an agent-facing research server, spanning search lifecycle, workspace CRUD, owner demands, providers, review scanning, and guidance. The tools are largely justified by distinct workflows, but the count is borderline and increases selection burden.
The surface covers lead-search lifecycle, workspace creation/read/update/research/learning, provider browsing and matching, owner-demand browsing and drafting, review scanning, and explanatory guidance. Minor gaps exist around explicit export or workspace deletion and owner-demand publishing, though some of these may be intentionally outside the MCP scope or handled elsewhere.
Available Tools
21 toolsbrowse_owner_demandsBrowse published owner requestsBRead-onlyIdempotentInspect
Browse public business requests with current website-control proof. A posted request is owner-reported need, not a funded contract, verified budget, or permission to contact outside the application flow.
Inputs: limit, query, cursor, industry, +1 more. Returns: caveat, notice, demands, nextCursor
browse_service_providersBrowse published provider profilesBRead-onlyIdempotentInspect
Read provider-declared capabilities, portfolio URLs, markets, and capacity. These are self-reported and do not imply a skill or performance endorsement.
Inputs: limit, query, cursor, industry, +1 more. Returns: caveat, notice, providers, nextCursor
cancel_lead_searchCancel a lead searchADestructiveIdempotentInspect
Cancel a queued or running search job. Completed and failed jobs remain immutable.
Inputs: id (required), jobToken (required). Returns: id, status, canceledAt
create_opportunity_workspaceCreate a private opportunity workspaceAInspect
Save a research thesis workspace and declared capabilities. This does not run research or establish demand. Use idempotencyKey to safely retry creation.
Inputs: name (required), profile, idempotencyKey. Returns: revision, workspace
create_owner_demand_draftPrepare a private owner requestAInspect
Create a private draft request. Publishing is a separate owner-controlled action requiring website control and explicit review of public fields. This tool never publishes, contacts providers, creates a contract, or moves money.
Inputs: title (required), problem (required), website (required), industry (required), +5 more. Returns: demand
explain_crawdarExplain Crawdar searchARead-onlyIdempotentInspect
Get result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.
Inputs: no named parameters. Returns: guidance, interfaces, resultLanes
get_lead_searchGet a lead search pageARead-onlyIdempotentInspect
Read job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.
Inputs: id (required), jobToken (required), view, limit, +1 more. Returns: id, error, status, results, +11 more
get_opportunity_learningReview recorded opportunity outcomesARead-onlyIdempotentInspect
Read your private evidence funnel and failure feedback plus sufficiently diverse, jointly consented public outcome aggregates. Requires verified account identity or linked API key. Rates describe recorded cohorts and do not prove causal effectiveness or future results.
Inputs: no named parameters. Returns: funnel, feedback, publicLearning, recommendations
get_opportunity_workspaceRead a private opportunity workspaceARead-onlyIdempotentInspect
Get the current workspace and revision before updating. Evidence, contradictory findings, manually recorded validation milestones, and monitor configuration remain private to the account.
Inputs: id (required). Returns: revision, workspace
list_opportunity_workspacesList private opportunity workspacesARead-onlyIdempotentInspect
List research workspaces owned by your verified account. Requires an account-linked API key or signed-in identity; no guest access or public Atlas.
Inputs: no named parameters. Returns: workspaces
match_demand_providersCompare providers for a requestBRead-onlyIdempotentInspect
Rank one page of up to 50 published providers by declared skill labels and market fit. Public consented outcome context remains separate from provider ratings. Use nextCursor for more candidates; missing data is unknown.
Inputs: demandId (required), cursor, industry, geography. Returns: caveat, notice, matches, nextCursor
refine_lead_searchRefine a lead searchAInspect
Create a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.
Inputs: id (required), jobToken (required), brief, limit, +4 more. Returns: id, status, cacheHit, jobToken, +6 more
research_businessesResearch businesses from a briefARead-onlyInspect
Use for a quick synchronous search when the user supplies one natural-language brief and can wait for results in the current tool call. For durable progress, retry, export, or large agent workflows, use start_lead_search instead.
Inputs: brief (required), limit, fields, offset, +3 more. Returns: limit, offset, hasMore, results, +10 more
research_opportunity_workspaceResearch public problems into a workspaceBInspect
Run a bounded public review scan of up to three businesses and retain sourced findings in your private workspace. Requires current revision. Sampled complaints are investigation leads, not owner-confirmed needs or purchase proof. Uses normal provider limits; do not launch duplicate concurrent scans.
Inputs: id (required), revision (required), target, geography, +1 more. Returns: revision, workspace
retry_lead_searchRetry a stopped lead searchAInspect
Create a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.
Inputs: id (required), jobToken (required). Returns: id, status, cacheHit, jobToken, +6 more
sandbox_businessesTest the Crawdar contractARead-onlyIdempotentInspect
Return deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.
Inputs: target, geography. Returns: limit, offset, hasMore, results, +10 more
scan_review_pain_pointsFind recurring customer complaintsARead-onlyInspect
Scan a named business or discover up to three businesses for recent recurring complaints. Returns individually sourced reviews and possible technical solutions. Coverage is sampled; unavailable reviews never mean no problems. Five scans per day. Google reviews require a configured provider.
Inputs: target, website, business, geography, +2 more. Returns: id, status, reports, limitations
search_businessesSearch businesses with structured criteriaARead-onlyInspect
Use for a quick synchronous search when target, geography, and qualification fields are already structured. Use research_businesses for a plain-language brief, or start_lead_search for durable asynchronous work.
Inputs: target (required), geography (required), limit, fields, +4 more. Returns: limit, offset, hasMore, results, +10 more
search_problem_graphSearch the shared problem graphCRead-onlyIdempotentInspect
Read Crawdar editorial research, explicitly contributed observations, and website-control-confirmed owner demand across markets. Editorial research does not mean the featured business joined or confirmed a problem. Includes source URLs, dates, support and contradiction. Private workspaces are never included automatically. Contributions and owner reports are not independently verified facts or purchase intent.
Inputs: host, limit, query, cursor, +3 more. Returns: edges, items, nodes, caveat, +2 more
start_lead_searchStart a durable lead searchAInspect
Use for the recommended durable asynchronous workflow. Creates a private queued search job and returns a job id plus jobToken for progress polling, cursor paging, refinement, retry, cancellation, and CSV or JSON export.
Inputs: brief, limit, fields, target, +3 more. Returns: id, status, cacheHit, jobToken, +6 more
update_opportunity_workspaceUpdate an opportunity workspaceAInspect
Apply one validated command with the latest revision. A 409 means re-read before retrying. Public signals never establish payment or purchase intent; commercial milestones require separately supplied attributable evidence. Does not contact businesses or execute delivery.
Inputs: id (required), command (required), revision (required). Returns: revision, workspace
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Paid web research, news, company briefs, fact-checks and US weather data for AI agents
Grounded financial research for agents: filings, transcripts, news across US and Asia markets.
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Live context for your agent: competitors, mentions and markets, from public data.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables agents to search SEC filings, earnings transcripts, and EU regulations with ready-to-cite evidence, including exact passages and source links.Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to research US companies from official public data, covering SEC EDGAR filings, XBRL financials, Form 4 insider trades, cross-company financial comparisons, and Secretary of State business-entity lookups for NY, CO, OR, CT, and PA. Responses are compact JSON with source URLs and paging options, keeping token usage low without requiring API keys.1074 npmMIT
- AlicenseAqualityBmaintenanceEnables agents to perform compact, cited web research within caller-set token caps, returning direct answers, short verbatim quotes, numbered sources, and noted gaps.544 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to perform institutional-grade research by retrieving and validating company, financial, industry, news, litigation, and funding data, then generating cited reports in Markdown, HTML, or PDF.-
Glama MCP Gateway
Add one secure layer between your agents and this server.