io.github.MetriLLM/metrillm MCP Server

io.github.MetriLLM/metrillm

What is the io.github.MetriLLM/metrillm MCP server?

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

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "metrillm": {
      "command": "npx",
      "args": [
        "-y",
        "metrillm-mcp"
      ]
    }
  }
}

Pay-per-use AI and data tools via x402: image, video, music, voice, search, crypto. USDC.

Active

Structural code navigation, persistent memory, and Bash output compaction for AI coding agents—97.9% benchmark score at -80% tokens.

1.1k

Python

MIT

Look up amateur radio repeaters from RepeaterBook.com by location, band, and mode.

Active

Leased dev environments — every server dies when its AI session ends.

Python

Apache-2.0

Active

Operate a k3s / Kubernetes cluster from your AI agent — safe-by-default MCP server.

Python

MIT

Active

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

Python

MIT