Gemini CLI LLM Margin estimate_ai_service

How to: Gemini CLI LLM Margin estimate_ai_service

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

Add LLM Margin to Gemini CLI

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

{
  "mcpServers": {
    "llm-margin": {
      "httpUrl": "https://llmmargin.com/mcp"
    }
  }
}

02
Save the file and restart Gemini CLI.
03
Ask for something estimate_ai_service does. Gemini CLI lists the server's tools on connect and calls estimate_ai_service itself — you do not invoke it by name.
04
If nothing happens, check the server is running and that LLM Margin'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

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 14 November 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.

LLM Margin MCP server