Schema | Firecrawl MCP Toolkit

Firecrawl MCP Toolkit

Describes the environment variables required to run the server.

Name	Required	Description	Default
`FIRECRAWL_HTTP2`	No	Enable HTTP/2 with '1'.	0
`FIRECRAWL_API_KEY`	Yes	Firecrawl API key.
`FIRECRAWL_BASE_URL`	No	Firecrawl API base URL. Set this for self-hosted services.	https://api.firecrawl.dev/v2
`FIRECRAWL_KEEPALIVE`	No	Maximum keepalive connections.	20
`FIRECRAWL_MAX_WORKERS`	No	Number of worker processes.	10
`FIRECRAWL_RETRY_COUNT`	No	Maximum retry count.	3
`FIRECRAWL_MCP_SSE_HOST`	No	SSE host.	127.0.0.1
`FIRECRAWL_MCP_SSE_PORT`	No	SSE port.	7001
`FIRECRAWL_MCP_HTTP_HOST`	No	HTTP host.	127.0.0.1
`FIRECRAWL_MCP_HTTP_PORT`	No	HTTP port.	7001
`FIRECRAWL_MCP_LOCK_FILE`	No	Lock file path.	/tmp/firecrawl_mcp.lock
`FIRECRAWL_MCP_ENABLE_SSE`	No	Enable SSE transport.	0
`FIRECRAWL_MAX_CONNECTIONS`	No	Maximum HTTP connections.	200
`FIRECRAWL_MCP_ENABLE_HTTP`	No	Enable HTTP transport.	0
`FIRECRAWL_MCP_ENABLE_STDIO`	No	Enable STDIO transport.	0
`FIRECRAWL_RETRY_BASE_DELAY`	No	Base retry delay in seconds.	0.5
`FIRECRAWL_ENDPOINT_RETRYABLE`	No	Per-endpoint retry configuration.	{"scrape": false}
`FIRECRAWL_ENDPOINT_CONCURRENCY`	No	Per-endpoint concurrency limits.	{"search":10,"scrape":2}
`FIRECRAWL_MAX_CONCURRENT_REQUESTS`	No	Maximum concurrent requests.	200

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Joey-Kot/firecrawl-toolkit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server