Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Mirrored from https://github.com/Camo67/composio.git
Synced Nov 21, 06:00 UTC
| 1 | --- |
| 2 | type: "reference" |
| 3 | title: "Firecrawl" |
| 4 | description: "Public support knowledge for Firecrawl." |
| 5 | category: "authentication" |
| 6 | visibility: "public" |
| 7 | timestamp: "2026-06-24T00:00:00Z" |
| 8 | tags: |
| 9 | - "firecrawl" |
| 10 | --- |
| 11 | # Firecrawl |
| 12 | |
| 13 | |
| 14 | ## Firecrawl uses API-key auth, not OAuth; provide a Firecrawl API key |
| 15 | |
| 16 | Firecrawl does not use a Composio-managed OAuth/test connector flow. It is an API-key toolkit, so the customer needs a Firecrawl API key, and in many cases their own Firecrawl subscription/account. If an MCP client does not prompt for the key, provide it through the connection flow or explicitly tell the agent/client to use the Firecrawl API key for authentication. |
| 17 | |
| 18 | ## Create a Firecrawl API-key connected account with generic_api_key |
| 19 | |
| 20 | For Firecrawl API-key auth, create the connected account with `authScheme: "API_KEY"` and a value object containing `status: "ACTIVE"` and `generic_api_key: "fc-..."`. The exact required key names can be checked from the toolkit metadata/connection initiation fields. |
| 21 | |
| 22 | ## FIRECRAWL_SEARCH may be hidden by default tool list limits |
| 23 | |
| 24 | If `FIRECRAWL_SEARCH` or other Firecrawl tools are missing from a tools list, increase the list limit or paginate. The default list can return only the first 20 tools, so request a higher limit such as `limit=1000` when fetching Firecrawl tools. |
| 25 | |
| 26 | ## Batch fewer URLs or raise timeout for long Firecrawl scrape jobs |
| 27 | |
| 28 | For Firecrawl scrape timeouts, reduce the number of links per request, such as batching 1-2 links at a time for complex pages, or increase the scrape timeout if the tool call supports it. A useful starting value is `timeout: 120000` for roughly a 2-minute timeout. |
| 29 | |
| 30 | ## Firecrawl API base URL is https://api.firecrawl.dev/v1 |
| 31 | |
| 32 | The Firecrawl API base URL is `https://api.firecrawl.dev/v1`. If a customer must manually enter a base URL to unblock a connection or custom call, use that value, while treating the need for manual entry as a product/tooling issue if the toolkit should have supplied it automatically. |
| 33 | |
| 34 | ## Use FIRECRAWL_SCRAPE or FIRECRAWL_EXTRACT for web-content retrieval |
| 35 | |
| 36 | For website content retrieval with Firecrawl, use `FIRECRAWL_SCRAPE` to scrape page content or `FIRECRAWL_EXTRACT` for extraction-style workflows. For broader web search, Composio Search may be a better fit depending on the use case. |
| 37 | |
| 38 | ## Connect MCP sessions are tied to individual consumer accounts, not a shared workspace |
| 39 | |
| 40 | For Connect MCP on the For You side, each user's MCP session is tied to their own Composio consumer account, not the shared workspace context. A Firecrawl connection created under one user's account/workspace will not automatically appear for colleagues in Claude. Each colleague should create/connect their own Firecrawl account connection for their individual Connect MCP session. |