Gemini CLI Claidex MCP query_failure_graph

How to: Gemini CLI Claidex MCP query_failure_graph

client:Gemini CLI transport:streamable-http tool:query_failure_graph

Add Claidex MCP to Gemini CLI

01
Open ~/.gemini/settings.json and merge this in. Keep any servers already there.

{
  "mcpServers": {
    "failure-intelligence": {
      "httpUrl": "https://app.claidex.com/api/mcp"
    }
  }
}

02
Save the file and restart Gemini CLI.
03
Ask for something query_failure_graph does. Gemini CLI lists the server's tools on connect and calls query_failure_graph itself — you do not invoke it by name.
04
If nothing happens, check the server is running and that Claidex MCP's identifier in your config matches the one above exactly.

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

Set these first

Claidex MCP will not start until these are set, so query_failure_graph never becomes available.

CLAIDEX_MCP_URL
CLAIDEX_MCP_API_KEY

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what the server actually exposes, not what its listing claims.

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.

Claidex MCP MCP server