# Crawdar Business Research (remote · crawdar.com)

Evidence-backed public business research for agents with compact, pageable output.

- Trust score: 79/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

> **Recent critical change**: Authorization (2026-08-22). See the changelog below before you install this server.

## Components

- remote · `crawdar.com`: 79/100 (this document), [markdown](https://verifymcp.io/servers/com-crawdar-business-research/api-mcp.md), [page](https://verifymcp.io/servers/com-crawdar-business-research/api-mcp)

## Channel facts

- Endpoint: `https://crawdar.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.4.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_lead_search).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1233 tokens (~123/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Crawdar Business Research MCP server?

Crawdar Business Research is a hosted endpoint at https://crawdar.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-crawdar-business-research 'https://crawdar.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-crawdar-business-research": {
      "url": "https://crawdar.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-crawdar-business-research": {
      "type": "http",
      "url": "https://crawdar.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-crawdar-business-research]
url = "https://crawdar.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-crawdar-business-research": {
      "type": "remote",
      "url": "https://crawdar.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-crawdar-business-research --url 'https://crawdar.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-crawdar-business-research:
    url: "https://crawdar.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-crawdar-business-research": {
      "Transport": "http",
      "Url": "https://crawdar.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-crawdar-business-research -t streamable-http -u 'https://crawdar.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-crawdar-business-research": {
      "type": "http",
      "url": "https://crawdar.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 79, +1)

- [security] Stability: 0.97 → pass

### 2026-09-18 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 73, 0)

- [functional regression] Tool coverage: 100% → 87%
- [functional] Server version: 1.4.2 → 1.5.0
- [functional] New tool “scan_review_pain_points”

### 2026-09-07 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

## MCP tools (10)

### `scan_review_pain_points` (~103 tokens)

Find recurring customer complaints

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.

Input parameters:

- `business` (string)
- `geography` (string)
- `googlePlaceId` (string)
- `reviewUrls` (array)
- `target` (string)
- `website` (string)

Output parameters:

- `id` (string)
- `limitations` (string)
- `reports` (array)
- `status` (string)

### `research_businesses` (~176 tokens)

Research businesses from a brief

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.

Input parameters:

- `brief` (string, required): Example: Independent veterinary clinics in Berlin with an active first-party website. Exclude directories and chains.
- `fields` (array): Business fields to retain. Website and source evidence remain available for verification.
- `geography` (string): Optional explicit geography. Use when the brief does not make location clear.
- `includeDiagnostics` (boolean): Include source status and explained exclusions.
- `limit` (integer): Maximum businesses in this response page.
- `offset` (integer): Zero-based result offset for this response page.
- `output`: Compact minimizes tokens. Full preserves every returned field.

Output parameters:

- `diagnostics` (object): Source status and explained candidate exclusions.
- `durationMs` (integer)
- `hasMore` (boolean): Whether another result page is available.
- `limit` (integer): Maximum prospects requested for this page.
- `nextOffset` (integer|null): Offset for the next synchronous result page, or null when complete.
- `offset` (integer): Zero-based offset of this page.
- `remainingFreeSearches` (integer)
- `requestId` (string): Request identifier for support and diagnostics.
- `resultCount` (integer): Total accepted prospects before response pagination.
- `results` (array)
- `returnedCount` (integer): Prospects returned in this response page.
- `schemaVersion` (string): Version of the result contract.
- `searchedSources` (array): Discovery and first-party source types consulted.
- `warnings` (array): Limitations the agent should retain with downstream data.

### `search_businesses` (~169 tokens)

Search businesses with structured criteria

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.

Input parameters:

- `fields` (array): Business fields to retain. Website and source evidence remain available for verification.
- `geography` (string, required): City, region, country, or Worldwide.
- `includeDiagnostics` (boolean): Include source status and explained exclusions.
- `limit` (integer): Maximum businesses in this response page.
- `offset` (integer): Zero-based result offset for this response page.
- `output`: Compact minimizes tokens. Full preserves every returned field.
- `qualifier` (string): Optional required signals and exclusions that can be checked in public evidence.
- `target` (string, required): Business type or concise target.

Output parameters:

- `diagnostics` (object): Source status and explained candidate exclusions.
- `durationMs` (integer)
- `hasMore` (boolean): Whether another result page is available.
- `limit` (integer): Maximum prospects requested for this page.
- `nextOffset` (integer|null): Offset for the next synchronous result page, or null when complete.
- `offset` (integer): Zero-based offset of this page.
- `remainingFreeSearches` (integer)
- `requestId` (string): Request identifier for support and diagnostics.
- `resultCount` (integer): Total accepted prospects before response pagination.
- `results` (array)
- `returnedCount` (integer): Prospects returned in this response page.
- `schemaVersion` (string): Version of the result contract.
- `searchedSources` (array): Discovery and first-party source types consulted.
- `warnings` (array): Limitations the agent should retain with downstream data.

### `sandbox_businesses` (~61 tokens)

Test the Crawdar contract

Return deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.

Input parameters:

- `geography` (string): Fictional location echoed into deterministic test results.
- `target` (string): Fictional business type echoed into deterministic test results.

Output parameters:

- `diagnostics` (object): Source status and explained candidate exclusions.
- `durationMs` (integer)
- `hasMore` (boolean): Whether another result page is available.
- `limit` (integer): Maximum prospects requested for this page.
- `nextOffset` (integer|null): Offset for the next synchronous result page, or null when complete.
- `offset` (integer): Zero-based offset of this page.
- `remainingFreeSearches` (integer)
- `requestId` (string): Request identifier for support and diagnostics.
- `resultCount` (integer): Total accepted prospects before response pagination.
- `results` (array)
- `returnedCount` (integer): Prospects returned in this response page.
- `schemaVersion` (string): Version of the result contract.
- `searchedSources` (array): Discovery and first-party source types consulted.
- `warnings` (array): Limitations the agent should retain with downstream data.

### `start_lead_search` (~193 tokens)

Start a durable lead search

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.

Input parameters:

- `brief` (string): Natural-language business, geography, required signals, and exclusions. Use this instead of separate target and geography.
- `fields` (array): Business fields to retain. Website and source evidence remain available for verification.
- `geography` (string): City, region, country, or Worldwide. Required with target when brief is omitted.
- `idempotencyKey` (string): Stable key for safely retrying the same job creation request.
- `limit` (integer): Maximum accepted prospects retained by the job.
- `qualifier` (string): Publicly verifiable requirements and exclusions.
- `target` (string): Business type or concise ideal-customer target. Pair with geography when brief is omitted.

Output parameters:

- `cacheHit` (boolean)
- `cancelUrl` (string): Authenticated REST URL for canceling queued or running work.
- `expiresInSeconds` (integer): Seconds until the private job and token expire.
- `exportUrl` (string): Authenticated CSV export URL. Add format=json for JSON.
- `id` (string): Stable job identifier. Use it with jobToken in every lifecycle call.
- `jobToken` (string): Private bearer token required to read, refine, or export this job.
- `resultCount` (integer)
- `retryUrl` (string): Authenticated REST URL for creating a replacement after retryable failure.
- `status`: Current durable job state.
- `statusUrl` (string): Authenticated REST URL for job status and result pages.

### `get_lead_search` (~122 tokens)

Get a lead search page

Read job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.

Input parameters:

- `cursor` (string): Opaque nextCursor from the previous response.
- `id` (string, required): Job id returned by start_lead_search, refine_lead_search, or retry_lead_search.
- `jobToken` (string, required): Private token returned with the job. Do not log or share it.
- `limit` (integer): Maximum prospects in this result page.
- `view`: Compact minimizes tokens. Full retains detailed evidence fields.

Output parameters:

- `completedAt` (string|null)
- `createdAt` (string)
- `diagnostics` (object)
- `error` (string)
- `errorCode` (string)
- `id` (string)
- `nextCursor` (string|null)
- `progress` (object)
- `resultCount` (integer)
- `results` (array)
- `retryAfter` (integer)
- `returned` (integer)
- `searchedSources` (array)
- `status`
- `warnings` (array)

### `refine_lead_search` (~157 tokens)

Refine a lead search

Create a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.

Input parameters:

- `brief` (string): Replacement natural-language brief for the new job.
- `fields` (array): Business fields to retain. Website and source evidence remain available for verification.
- `geography` (string): Replacement city, region, country, or Worldwide.
- `id` (string, required): Completed source job id returned by an earlier durable search call.
- `jobToken` (string, required): Private token belonging to the source job.
- `limit` (integer): Maximum prospects retained by the new job.
- `qualifier` (string): Replacement public requirements and exclusions.
- `target` (string): Replacement business target for the new job.

Output parameters:

- `cacheHit` (boolean)
- `cancelUrl` (string): Authenticated REST URL for canceling queued or running work.
- `expiresInSeconds` (integer): Seconds until the private job and token expire.
- `exportUrl` (string): Authenticated CSV export URL. Add format=json for JSON.
- `id` (string): Stable job identifier. Use it with jobToken in every lifecycle call.
- `jobToken` (string): Private bearer token required to read, refine, or export this job.
- `resultCount` (integer)
- `retryUrl` (string): Authenticated REST URL for creating a replacement after retryable failure.
- `status`: Current durable job state.
- `statusUrl` (string): Authenticated REST URL for job status and result pages.

### `retry_lead_search` (~62 tokens)

Retry a stopped lead search

Create a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.

Input parameters:

- `id` (string, required): Failed or timed-out source job id.
- `jobToken` (string, required): Private token belonging to the source job.

Output parameters:

- `cacheHit` (boolean)
- `cancelUrl` (string): Authenticated REST URL for canceling queued or running work.
- `expiresInSeconds` (integer): Seconds until the private job and token expire.
- `exportUrl` (string): Authenticated CSV export URL. Add format=json for JSON.
- `id` (string): Stable job identifier. Use it with jobToken in every lifecycle call.
- `jobToken` (string): Private bearer token required to read, refine, or export this job.
- `resultCount` (integer)
- `retryUrl` (string): Authenticated REST URL for creating a replacement after retryable failure.
- `status`: Current durable job state.
- `statusUrl` (string): Authenticated REST URL for job status and result pages.

### `cancel_lead_search` (~52 tokens)

Cancel a lead search

Cancel a queued or running search job. Completed and failed jobs remain immutable.

Input parameters:

- `id` (string, required): Queued or running job id.
- `jobToken` (string, required): Private token belonging to the job.

Output parameters:

- `canceledAt` (string)
- `id` (string)
- `status`

### `explain_crawdar` (~32 tokens)

Explain Crawdar search

Get result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.

Output parameters:

- `guidance` (array)
- `interfaces` (object)
- `resultLanes` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-crawdar-business-research/api-mcp#diagnostics

## Score history

- 2026-09-20: 79
- 2026-09-19: 78
- 2026-09-18: 78
- 2026-09-17: 77
- 2026-09-16: 77
- 2026-09-15: 76
- 2026-09-14: 76
- 2026-09-13: 75
- 2026-09-12: 75
- 2026-09-11: 74
- 2026-09-10: 74
- 2026-09-09: 73
- 2026-09-08: 73
- 2026-09-07: 73
- 2026-09-06: 73
- 2026-09-05: 72
- 2026-09-04: 72
- 2026-09-03: 71
- 2026-09-02: 71
- 2026-09-01: 71
- 2026-08-31: 70
- 2026-08-30: 70
- 2026-08-29: 69
- 2026-08-28: 69
- 2026-08-27: 68
- 2026-08-26: 68
- 2026-08-25: 62
- 2026-08-24: 62
- 2026-08-23: 61
- 2026-08-22: 60

## Common questions

### What is the Crawdar Business Research MCP server?

Crawdar Business Research is an MCP server listed in the public MCP registry as com.crawdar/business-research. Evidence-backed public business research for agents with compact, pageable output. This page covers its hosted endpoint (https://crawdar.com/api/mcp).

### Is the Crawdar Business Research MCP server safe to use?

Crawdar Business Research scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Crawdar Business Research MCP server expose?

Crawdar Business Research exposes 10 tools: scan_review_pain_points, research_businesses, search_businesses, sandbox_businesses, start_lead_search, and 5 more. Their descriptions and schemas cost roughly 1,127 tokens of context every time the server is loaded.

### Does the Crawdar Business Research MCP server require authentication?

No. We connected to Crawdar Business Research without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Crawdar Business Research MCP server still maintained?

Crawdar Business Research is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://crawdar.com/api/mcp
- Website: https://crawdar.com/agents
- Changelog RSS feed: https://verifymcp.io/servers/com-crawdar-business-research/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-crawdar-business-research/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-crawdar-business-research/api-mcp