firecrawl-mcp-server: "Client Closed or Failed to create" on Windows 11 — any fix?
firecrawl-mcp-server fails to connect on Windows 11 with "Client Closed or Failed to create" and "MCP error -32001: Request timed out", while other MCP servers in the same client work fine. The issue also reproduces on Windows 10 with WSL. Is there a working fix?
Originally asked on GitHub: https://github.com/firecrawl/firecrawl-mcp-server/issues/36
3 answers
Status: Still open — as of May 2025 there is no confirmed fix or maintainer response in this thread.
The thread reports that firecrawl-mcp-server fails to connect on Windows 11 while other MCP servers in the same client work normally. The client shows "Client Closed or Failed to create", and one user reported "Failed to connect to MCP server: MCP error -32001: Request timed out". The issue also reproduces on Windows 10 with WSL.
The only concrete fix suggested was to remove the
-yargument option from the firecrawl command in your MCP client config. One user tested this and reported it did not fix the error, so it is not a reliable workaround. One commenter said they tried "many solutions" but did not list them, so no working fix appears in this thread.General debugging advice (not from the thread): run the exact firecrawl command from your MCP config manually in a terminal first. If it starts and prints a server-ready message, the command itself is fine and the problem is in how the client spawns it; if it crashes, you will see the server's own error output, which is more specific than the client's generic "request timed out" message.
Did this work for you?What @aneym tried on GitHub (Didn't work)
After comment 4 suggested removing the
-yargument from the firecrawl-mcp-server launch command, this user tested it and reported the same issue persisted.Did this work for you?What @VipulSoniwork tried on GitHub (Outcome unclear)
A commenter confirmed the same failure while their other MCP servers connected fine, and said they had tried "many solutions" without listing any specifics.
Did this work for you?
Related questions
- How do I make firecrawl-mcp-server use a self-hosted Firecrawl URL?
- How do I raise the 3/min RATE_LIMIT in firecrawl-mcp-server for a self-hosted Firecrawl instance?
- firecrawl_check_batch_status returns a localhost URL that doesn't work in Docker — how to get batch results?
- How to fix firecrawl-mcp hanging on stdio during init and tool calls?
- Firecrawl MCP server not deployed on Smithery after repo moved to Mendable