Cursor MCP client confused by multiple tenants of same system with MCP servers

Hey, thanks for the report. This is a known issue: when multiple MCP servers have tools with the same names, Cursor routes all calls to one server instead of the correct one.

Interesting detail: the bug was fixed in 2.3.21, but all fix confirmations were for local STDIO servers. You’re using remote HTTP servers, so it’s possible the fix didn’t cover that transport.

A couple questions:

  • If you leave only one server in mcp.json, do calls to it work correctly?
  • Can you share a chat example that shows the call going to the wrong server?

Workarounds for now:

  • Rename the tools in the server code: if you have access to the frappe_assistant code, add a suffix like _staging or _harvestmaster to the tool names. Confirmed to work.
  • Start a new chat: routing may be cached per session.

I’ll pass the info about the HTTP transport issue to the team.