Evidence-backed public business research for agents with compact, pageable output.
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://crawdar.com/api/mcp10 tools · 4695msscan_review_pain_pointsScan 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.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.
| Parameter | Type | Description |
|---|---|---|
| business | string | — |
| website | string | — |
| target | string | — |
| geography | string | — |
| reviewUrls | array | — |
| googlePlaceId | string | — |
research_businessesUse 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.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.
| Parameter | Type | Description |
|---|---|---|
| brief* | string | Example: Independent veterinary clinics in Berlin with an active first-party website. Exclude directories and chains. |
| geography | string | Optional explicit geography. Use when the brief does not make location clear. |
| fields | array | Business fields to retain. Website and source evidence remain available for verification. |
| output | — | Compact minimizes tokens. Full preserves every returned field. |
| limit | integer | Maximum businesses in this response page. |
| offset | integer | Zero-based result offset for this response page. |
| includeDiagnostics | boolean | Include source status and explained exclusions. |
search_businessesUse 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.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.
| Parameter | Type | Description |
|---|---|---|
| target* | string | Business type or concise target. |
| geography* | string | City, region, country, or Worldwide. |
| qualifier | string | Optional required signals and exclusions that can be checked in public evidence. |
| fields | array | Business fields to retain. Website and source evidence remain available for verification. |
| output | — | Compact minimizes tokens. Full preserves every returned field. |
| limit | integer | Maximum businesses in this response page. |
| offset | integer | Zero-based result offset for this response page. |
| includeDiagnostics | boolean | Include source status and explained exclusions. |
sandbox_businessesReturn deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.Return deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.
| Parameter | Type | Description |
|---|---|---|
| target | string | Fictional business type echoed into deterministic test results. |
| geography | string | Fictional location echoed into deterministic test results. |
start_lead_searchUse 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.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.
| Parameter | Type | Description |
|---|---|---|
| brief | string | Natural-language business, geography, required signals, and exclusions. Use this instead of separate target and geography. |
| target | string | Business type or concise ideal-customer target. Pair with geography when brief is omitted. |
| geography | string | City, region, country, or Worldwide. Required with target when brief is omitted. |
| qualifier | string | Publicly verifiable requirements and exclusions. |
| fields | array | Business fields to retain. Website and source evidence remain available for verification. |
| limit | integer | Maximum accepted prospects retained by the job. |
| idempotencyKey | string | Stable key for safely retrying the same job creation request. |
get_lead_searchRead job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.Read job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.
| Parameter | Type | Description |
|---|---|---|
| id* | string | Job id returned by start_lead_search, refine_lead_search, or retry_lead_search. |
| jobToken* | string | Private token returned with the job. Do not log or share it. |
| cursor | string | Opaque nextCursor from the previous response. |
| limit | integer | Maximum prospects in this result page. |
| view | — | Compact minimizes tokens. Full retains detailed evidence fields. |
refine_lead_searchCreate a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.Create a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.
| Parameter | Type | Description |
|---|---|---|
| id* | string | Completed source job id returned by an earlier durable search call. |
| jobToken* | string | Private token belonging to the source job. |
| brief | string | Replacement natural-language brief for the new job. |
| target | string | Replacement business target for the new job. |
| geography | string | Replacement city, region, country, or Worldwide. |
| qualifier | string | Replacement public requirements and exclusions. |
| fields | array | Business fields to retain. Website and source evidence remain available for verification. |
| limit | integer | Maximum prospects retained by the new job. |
retry_lead_searchCreate a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.Create a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.
| Parameter | Type | Description |
|---|---|---|
| id* | string | Failed or timed-out source job id. |
| jobToken* | string | Private token belonging to the source job. |
cancel_lead_searchCancel a queued or running search job. Completed and failed jobs remain immutable.Cancel a queued or running search job. Completed and failed jobs remain immutable.
| Parameter | Type | Description |
|---|---|---|
| id* | string | Queued or running job id. |
| jobToken* | string | Private token belonging to the job. |
explain_crawdarGet result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.Get result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.
No input schema was published for this tool.
10 of 10 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Evidence-backed public business research for agents with compact, pageable output.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.