Skip to content

FitLLM MCP server

Which servers in the official MCP registry are FitLLM's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-15

← Back to FitLLM

Whose server it is
  • Registry namerun.fitllm/fitllmverified in the MCP registry

The registry name sits under fitllm.run. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-15
  • Stateanswerschecked 2026-10-15
  • Tools3
  • Server calls itselffitllm
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-15 the server answered initialize and tools/list without a sign-in. First answer in 142 ms.

Measured dailydaily checks: 2, the first on 2026-10-19
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer183 ms
  • Space in an agent's context≈ 910 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-15
  • check_llm_fit

    Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead…

  • what_fits_on_hardware

    Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?"…

  • list_supported

    List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "fitllm": {
      "type": "http",
      "url": "https://fitllm.run/api/mcp"
    }
  }
}

OpenAPI spec

2 paths, read 2026-10-15. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.