Log inSubmit server
TokenMark logo

TokenMark

Provides live local-LLM benchmarks, hardware-aware model recommendations, and reviewed benchmark submission tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install TokenMark

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "tokenmark": {
      "command": "npx",
      "args": [
        "-y",
        "@altronis/tokenmark-mcp"
      ],
      "env": {
        "TOKENMARK_URL": "YOUR_VALUE_HERE",
        "TOKENMARK_TOKEN": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

TokenMark MCP server connects agents to measured local-LLM benchmark data from TokenMark. It recommends models and configurations for hardware such as Strix Halo, DGX Spark, and Mac systems, using decode speed, quantization, backend, and task preferences. Agents can also search benchmark records, inspect hardware details, and submit repositories or measured results for human review. Reach for it when model selection depends on real device performance rather than estimated numbers.

Use cases

  • Recommend a local model for coding on Strix Halo
  • Compare tracked configurations by hardware or model
  • Inspect hardware specifications and Singapore prices
  • Search benchmark records for a model or configuration
  • Submit measured llama-bench results for review

Key features

  • Hardware-aware model recommendations
  • Measured decode-speed and configuration data
  • Hardware catalogue with source references
  • Model and configuration search
  • Human-reviewed benchmark submissions
  • Two-step confirmation for result submission

Tools13

What TokenMark lets your agent do. Expand a tool for its parameters.

Self-reported~46 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @altronis/tokenmark-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads748Package downloads in the last 30 days.
Last commit8d agoMost recent push to the default branch.
Tools exposed13Callable tools this server registers over MCP.

How TokenMark works

What the TokenMark MCP server does

The TokenMark MCP server gives MCP-compatible agents access to live benchmark records from TokenMark. Its primary use is selecting a local language model and configuration for a particular machine or workload. Recommendations are based on measured results and include performance information such as decode tokens per second, quantization, backend, and an explanation for the ranking. Each recommendation includes a source link.

The catalogue covers platforms including Strix Halo, Gorgon Halo, DGX Spark, and Mac Max or Ultra systems. Hardware lookups can return chip specifications, source references for those values, the systems that ship with the chip, and Singapore pricing. This makes the server useful when hardware selection and model selection are part of the same decision.

How it works

The TokenMark MCP server retrieves data live from https://tokenmark.app. It runs over stdio, so an MCP client starts the package locally with npx. Runtime dependencies are not required beyond the package execution environment. The service does not present estimates as measurements; recommendations and configuration results come from tracked benchmark data.

tokenmark_recommend accepts hardware and optional task or preference filters, then returns ranked picks. tokenmark_configs lists tracked configurations, with fastest results first, and identifies speculative runs such as MTP, DFlash, or draft-model configurations. tokenmark_search finds matching models and configurations, while tokenmark_hardware exposes the hardware catalogue.

Setup and configuration

Install the server in a compatible MCP client with:

Terminal
npx -y @altronis/tokenmark-mcp

For Claude Code, the documented command is:

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

Cline can add the same stdio server through its CLI or its VS Code MCP settings. Other clients can use a server entry with npx as the command and -y @altronis/tokenmark-mcp as its arguments.

Set TOKENMARK_URL to point the server at a different TokenMark endpoint. Most read operations need no sign-in. Sending measured results requires a one-time TokenMark CLI login on the same machine, or a TOKENMARK_TOKEN value when no home directory is available.

Tools and capabilities

The server exposes tools for recommendations, configuration listings, hardware details, and searches. It also supports contribution workflows:

  • Queue a GitHub or Hugging Face repository with tokenmark_submit.
  • Check a submission using tokenmark_submission_status.
  • Send measured benchmark output or manually supplied fields with tokenmark_submit_result.

Result submission uses a two-step confirmation process. A dry run returns a summary and confirmation code. The user must approve that summary before the same fields and code can be submitted for human review. Raw llama-bench or vllm bench serve output can be supplied, and explicit fields take precedence over parsed values.

Limitations and notes

The catalogue is limited to the hardware and benchmark data tracked by TokenMark. A missing platform or manually entered result can instead be submitted through the signed-in TokenMark form. Submission access is for review rather than immediate publication, and sign-in credentials last 90 days. Benchmark data is aggregated from public community results with attribution, so coverage depends on available submissions.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about TokenMark

TokenMark is an MCP server that connects AI agents to live TokenMark local-LLM benchmark data. Its main tools recommend models and configurations, list tracked benchmark runs, search models, inspect supported hardware, and submit repositories or measured results for human review.

Install it by running `npx -y @altronis/tokenmark-mcp` as an stdio MCP server. Claude Code and Cline also have documented add commands, while other MCP clients can use `npx` with the package name as its arguments.

Yes, TokenMark runs over standard stdio and can be configured in an MCP client such as Cursor. The README provides a generic MCP configuration using `npx -y @altronis/tokenmark-mcp`, rather than a Cursor-specific setup.

It ranks measured model and configuration results for supplied hardware, with optional task and preference filters. Results include measured decode speed, quantization, backend, a reason for the ranking, and a source link.

Sign in with `npx @altronis/tokenmark-cli login`, then use `tokenmark_submit_result`. First run a dry run to receive a summary and confirmation code; after approval, repeat the call with unchanged fields and that code.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewTokenMark AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/tokenmark?style=directory)](https://allmcps.com/mcp/tokenmark)
HTML Embed
<a href="https://allmcps.com/mcp/tokenmark"><img src="https://allmcps.com/api/badge/tokenmark?style=directory" alt="TokenMark on AllMCPs" /></a>