TokenMark MCP server

@altronis/tokenmark-mcp

An MCP server that gives Claude (and other agents) real local-LLM benchmark data + hardware-aware model recommendations from TokenMark.

Ask "what should I run on a Strix Halo for coding?" and the agent answers from measured configs (decode tok/s, quant, backend), each with a source link. It never invents numbers.

Add to Claude Code

claude mcp add tokenmark -- npx -y @altronis/tokenmark-mcp

Add to Cline

Cline CLI:

cline mcp add tokenmark --yes -- npx -y @altronis/tokenmark-mcp

Cline in VS Code: add the tokenmark entry from the JSON below to clinemcpsettings.json. Step-by-step notes for agents are in llms-install.md.

Add to any MCP client

Run the server over stdio:

npx -y @altronis/tokenmark-mcp

Or in a client config:

{
  "mcpServers": {
    "tokenmark": {
      "command": "npx",
      "args": ["-y", "@altronis/tokenmark-mcp"]
    }
  }
}

Tools

• tokenmarkrecommend**: { hardware, tasks?, prefer?, limit? } → ranked model + best-config picks (5 by default, 10 max) with measured tok/s + why.
• tokenmarkconfigs**: { model?, hardware?, limit? } → tracked benchmark configs, fastest first (25 by default, 50 max; matched gives the full count), with the run mode (speculative: true for MTP/DFlash/draft-model runs).
• tokenmarkhardware**: { platform? } → the hardware catalogue (Strix Halo, Gorgon Halo, DGX Spark, Mac Max/Ultra). With a platform: chip specs with a source per value, the boxes that ship it, Singapore prices.
• tokenmarksearch**: { term } → matching models/configs.
• tokenmarksubmit**: { repo, source?, note? } → queues a GitHub/Hugging Face repo with benchmark numbers for human review.
• tokenmarksubmissionstatus: { id } → where a submission is.
• tokenmarksubmitresult: { benchoutput?, pick?, model?, quant?, hardware?, backend?, decodetps?, prefilltps?, ctx?, concurrency?, ..., dryrun? } → sends a speed the user measured, for human review. Pass raw llama-bench or vllm bench serve output as benchoutput, or the fields by hand; fields you pass win over what it read. Sending takes two calls: dryrun: true returns a one-line summary and a confirm code; show the user the summary, and once they agree, call again with the same fields and confirm set to that code. A send without the code, or with fields changed since the dry run, is refused.

Sending measured speeds

tokenmarksubmitresult needs a one-time sign-in on the same machine, in a terminal:

npx @altronis/tokenmark-cli login

Approve the short code at https://tokenmark.app/cli. The sign-in can only send results for review and lasts 90 days; the server reads it on every call, so no restart is needed. Where there is no home directory, set TOKENMARK_TOKEN in the server's environment instead. A sign-in is only sent over https (or plain http to this machine), and every sign-in on the account can be revoked at https://tokenmark.app/cli.

Hardware missing from the catalogue, or a result typed in by hand, can also go through the signed-in form at https://tokenmark.app/submit.

Data is pulled live from https://tokenmark.app (override with TOKENMARK_URL). Zero runtime dependencies.

The same data in your terminal

The CLI lives in cli/ of this repo:

npx @altronis/tokenmark-cli recommend --hardware "Strix Halo" --tasks coding

The files in bin/ are the published builds, made from the TokenMark tracker that runs https://tokenmark.app.

MIT licensed. Data aggregated from public community benchmarks with attribution.