Categories › Knowledge & Everyday › Research, papers & reference data
Evidence-backed public business research for agents with compact, pageable output.
Remote server: your requests and data go to crawdar.com. Claude Code: claude mcp add --transport http crawdar-business-research https://crawdar.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
scan_review_pain_points — Scan a named business or discover up to three businesses for recent recurring complaints. Returns individually sourced reviews and possible research_businesses — 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 search_businesses — Use for a quick synchronous search when target, geography, and qualification fields are already structured. Use research_businesses for a plsandbox_businesses — Return deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.start_lead_search — Use for the recommended durable asynchronous workflow. Creates a private queued search job and returns a job id plus jobToken for progress pget_lead_search — Read job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.refine_lead_search — Create a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.retry_lead_search — Create a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.cancel_lead_search — Cancel a queued or running search job. Completed and failed jobs remain immutable.explain_crawdar — Get result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.list_opportunity_workspaces — List research workspaces owned by your verified account. Requires an account-linked API key or signed-in identity; no guest access or publiccreate_opportunity_workspace — Save a research thesis workspace and declared capabilities. This does not run research or establish demand. Use idempotencyKey to safely retget_opportunity_workspace — Get the current workspace and revision before updating. Evidence, contradictory findings, manually recorded validation milestones, and monitupdate_opportunity_workspace — Apply one validated command with the latest revision. A 409 means re-read before retrying. Public signals never establish payment or purchasresearch_opportunity_workspace — Run a bounded public review scan of up to three businesses and retain sourced findings in your private workspace. Requires current revision.search_problem_graph — Read Crawdar editorial research, explicitly contributed observations, and website-control-confirmed owner demand across markets. Editorial rbrowse_owner_demands — Browse public business requests with current website-control proof. A posted request is owner-reported need, not a funded contract, verifiedbrowse_service_providers — Read provider-declared capabilities, portfolio URLs, markets, and capacity. These are self-reported and do not imply a skill or performance match_demand_providers — Rank one page of up to 50 published providers by declared skill labels and market fit. Public consented outcome context remains separate froget_opportunity_learning — Read your private evidence funnel and failure feedback plus sufficiently diverse, jointly consented public outcome aggregates. Requires vericreate_owner_demand_draft — Create a private draft request. Publishing is a separate owner-controlled action requiring website control and explicit review of public fieNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.