Skip to content

AI tools, MCP servers and agent skills for benchmarks

59 MCP servers, 2 AI tools and 2 agent skills for benchmarks in AI models and LLM tooling, including Huggingface best, Huggingface community evals and rllm, most popular first. 44 of the 63 are listed as free or open source. Each one is written up from its own site or README, with pricing, platforms and alternatives.

Showing 1–5 of 5

  1. LLM Prover

    MCP server

    Compare models on cost and quality, score outputs and analyse agent runs

    Not checked yet
    • Remote
    • Paid
    • AI models and LLM tooling
  2. Woodstitch

    MCP server

    Paid human listeners judge your TTS audio in blind preference or human-vs-AI studies

    Runs locally
    • 13 tools
    • Paid
    • Design and media
  3. Extractive document summarizer that returns the source's own sentences, never new text

    Not checked yet
    • Remote
    • Paid
    • AI models and LLM tooling
  4. Xzar

    MCP server

    Test your agent on real tariff and patent decisions graded against the actual outcome

    Not checked yet
    • 9 tools
    • Remote
    • Paid
    • AI models and LLM tooling
  5. Ask several LLMs at once and get one judged answer through MCP

    Runs locally
    • 11 tools
    • Paid
    • AI models and LLM tooling