# Crawdar Business Research MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.crawdar%2Fbusiness-research
Registry id: `mcp-registry/com.crawdar/business-research`
Status: live (checked 2026-11-22T22:59:13.656Z)

## Verdict

Crawdar Business Research MCP server answered 100% of Glimind's liveness checks over 30 days, better than 43% of MCP servers, with 360 ms median handshake and 2 outages in 90 days. Its agent-readiness grade is A (90/100) across 21 tools, costing an agent about 5,569 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 43% of MCP servers |
| Median handshake latency | 360 ms | 34% of MCP servers |
| p95 handshake latency | 1122 ms | — |
| Checks in 30 days | 6,882 | — |
| Outages, 90 days | 2 | — |
| Median recovery | 31 min | — |
| Agent-readiness score | 90/100 (A) | 60% of MCP servers |
| Tools | 21 | — |
| Tool-list size for an agent | ~5,569 tokens | 28% of MCP servers |
| Days observed | 29 | — |

## Install

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

Claude Code:

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

## Tools (21)

- `browse_owner_demands`: Browse public business requests with current website-control proof. A posted request is owner-reported need, not a funded contract, verified budget, or permissi
- `browse_service_providers`: Read provider-declared capabilities, portfolio URLs, markets, and capacity. These are self-reported and do not imply a skill or performance endorsement.
- `cancel_lead_search`: Cancel a queued or running search job. Completed and failed jobs remain immutable.
- `create_opportunity_workspace`: Save a research thesis workspace and declared capabilities. This does not run research or establish demand. Use idempotencyKey to safely retry creation.
- `create_owner_demand_draft`: Create a private draft request. Publishing is a separate owner-controlled action requiring website control and explicit review of public fields. This tool never
- `explain_crawdar`: Get result semantics, limits, interface URLs, and safe operating guidance. This tool does not consume a search.
- `get_lead_search`: Read job status or one cursor-paginated result page. Keep jobToken private and pass nextCursor back unchanged.
- `get_opportunity_learning`: Read your private evidence funnel and failure feedback plus sufficiently diverse, jointly consented public outcome aggregates. Requires verified account identit
- `get_opportunity_workspace`: Get the current workspace and revision before updating. Evidence, contradictory findings, manually recorded validation milestones, and monitor configuration rem
- `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 public Atlas.
- `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 from provider ratings. 
- `refine_lead_search`: Create a new private search job by changing the brief or criteria of a completed job. The original job stays unchanged.
- `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 durable progress, re
- `research_opportunity_workspace`: Run a bounded public review scan of up to three businesses and retain sourced findings in your private workspace. Requires current revision. Sampled complaints 
- `retry_lead_search`: Create a replacement job when a prior job failed or exceeded its execution window. The original job stays available for audit.
- `sandbox_businesses`: Return deterministic fictional businesses without consuming provider capacity. Use this to test schemas, clients, and agent loops.
- `scan_review_pain_points`: Scan a named business or discover up to three businesses for recent recurring complaints. Returns individually sourced reviews and possible technical solutions.
- `search_businesses`: Use for a quick synchronous search when target, geography, and qualification fields are already structured. Use research_businesses for a plain-language brief, 
- `search_problem_graph`: Read Crawdar editorial research, explicitly contributed observations, and website-control-confirmed owner demand across markets. Editorial research does not mea
- `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 polling, cursor pagin
- `update_opportunity_workspace`: Apply one validated command with the latest revision. A 409 means re-read before retrying. Public signals never establish payment or purchase intent; commercial

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
