Metrillm

Overview

Metrillm is a Model Context Protocol (MCP) server: Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client. Because it speaks the Model Context Protocol, AI assistants can use Metrillm as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the npm package metrillm-mcp speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.2.6, published under the Apache-2.0 license, with source at MetriLLM/metrillm on GitHub.

On mcp.site, Metrillm sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Metrillm for MetriLLM, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "metrillm": {
      "command": "npx",
      "args": [
        "-y",
        "metrillm-mcp"
      ]
    }
  }
}