Metrillm MCP Server

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

Remote serverstreamable-http

What is the Metrillm MCP server?

Connect Metrillm to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client. The metrillm mcp server is what makes that connection.

What the server does

By default, production builds upload shared results to the official MetriLLM leaderboard (https://metrillm.dev).

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Credentials and setup notes

Configuration is passed through the environment: METRILLM_SUPABASE_URL, METRILLM_SUPABASE_ANON_KEY, METRILLM_PUBLIC_RESULT_BASE_URL, OLLAMA_HOST, LM_STUDIO_BASE_URL, LM_STUDIO_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by MetriLLM; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the Metrillm MCP server

{
  "mcpServers": {
    "metrillm": {
      "command": "npx",
      "args": ["-y", "metrillm"],
      "env": {
        "METRILLM_SUPABASE_URL": "your-value",
        "METRILLM_SUPABASE_ANON_KEY": "your-value",
        "METRILLM_PUBLIC_RESULT_BASE_URL": "your-value",
        "OLLAMA_HOST": "your-value",
        "LM_STUDIO_BASE_URL": "your-value",
        "LM_STUDIO_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
METRILLM_SUPABASE_URLEndpoint or connection string the server talks to.Yes
METRILLM_SUPABASE_ANON_KEYCredential the server authenticates with.Yes
METRILLM_PUBLIC_RESULT_BASE_URLEndpoint or connection string the server talks to.Yes
OLLAMA_HOSTEndpoint or connection string the server talks to.Optional
LM_STUDIO_BASE_URLEndpoint or connection string the server talks to.Yes
LM_STUDIO_API_KEYCredential the server authenticates with.Yes

Frequently asked questions

It connects Metrillm to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Metrillm directly.