Using local self-hosted Firecrawl instance is broken in v2.0.0

[dareima]

So far I was using the MCP server with a local self-hosted Firecrawl instance (Docker) and it worked fine.

Today I’ve noticed that the client now suddenly demands the FIRECRAWL_API_KEY to be set. That shouldn’t be necessary when FIRECRAWL_API_URL is set.

When setting a fake API Key, the MCP server only returns 404 errors. I suppose that is because the self-hosted instance isn’t used at all as soon as an API key is set. It seems to entirely ignore FORECRAWL_API_URL in that case.

Can someone confirm this? I didn’t change any configuration settings. The MCP server just went from functioning to error over the past few days. So I suppose it’s due to the latest update. I am using the MCP server via npx on stdio.

[dareima]

I ran some more tests this morning and can confirm my assumption.

Using self-hosted Firecrawl instances with the Firecrawl MCP-Server v2.0.0 is broken.

Forcing an older version like v1.12.0 via

    command: npx
    args: ["-y", "firecrawl-mcp@1.12.0"]

solves the issue and everything works again as intended, especially without providing an API key.