Evidence you can inspect.

Firecrawl MCP: connection plan

oauth_or_api_key · streamable-http · Setup source

https://mcp.firecrawl.dev/v2/mcp-oauth

Documentation checked: 2026-10-22 · Pricing: check_current_plan

{
  "web_research": {
    "inputs": [
      "text"
    ],
    "outputs": [
      "sources",
      "text"
    ]
  },
  "url_extraction": {
    "inputs": [
      "url"
    ],
    "outputs": [
      "text",
      "structured_data"
    ]
  }
}

1. Read current provider setup, allowed data handling and pricing.
2. Use OAuth at the listed endpoint, or Bearer API key at https://mcp.firecrawl.dev/v2/mcp.
3. Connect from your own client, initialize and list tools. Validate current inputSchema before using the example.
4. Try a small authorized task. Evaluate the output against your requirements.
5. Record a private attempt in your workspace. Publish feedback only after reviewing it.

{
  "tool": "firecrawl_search",
  "arguments": {
    "query": "Official MCP documentation",
    "limit": 3
  },
  "placeholder_values_require_replacement": true,
  "validate_current_provider_schema": true
}

Keyless features use a separate limited setup. This connection plan uses OAuth. Crawl scope, page permissions and usage credits apply.

Dated task assertions

Only the assertion below was checked. Local PDF tests use generated English documents. These results do not measure customer success, OCR accuracy or future availability. Tests older than 30 days do not count as a recent pass in task planning.

No execution test for this service. Do not treat documented capability as tested.

Repeat with your own criteria

SDK end-to-end checks: public research, local field provenance, unsupported scans and cancellation · Run the workflows

Run the local PDF fixtures with npm test in the downloadable example. Research test queries and tools are included in the JSON report. Initialize the provider and inspect tools/list before repeating them. No test runs automatically against your files.