MCPLow riskUnclaimed

TokenMark

Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.

sypherinsypherin/tokenmark-mcpUpdated Oct 9, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.sypherin/tokenmark-mcp",
  "description": "Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.",
  "title": "TokenMark",
  "repository": {
    "url": "https://github.com/sypherin/tokenmark-mcp",
    "source": "github"
  },
  "version": "0.3.0",
  "websiteUrl": "https://tokenmark.app",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@altronis/tokenmark-mcp",
      "version": "0.3.0",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@altronis/tokenmark-mcp@0.3.0
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #20.3.0latestOct 9, 2026
  2. #10.2.1Oct 7, 2026