MCPLow riskUnclaimed

tokcalc MCP Server

LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.

stevecrates489-commitsstevecrates489-commits/tokcalc★ 1Updated Oct 3, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json",
  "name": "io.github.stevecrates489-commits/tokcalc",
  "description": "LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.",
  "title": "tokcalc MCP Server",
  "repository": {
    "url": "https://github.com/stevecrates489-commits/tokcalc",
    "source": "github"
  },
  "version": "0.3.3",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@tokcalc/mcp-server",
      "version": "0.3.3",
      "transport": {
        "type": "stdio"
      }
    }
  ],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://tokcalc.vercel.app/api/mcp"
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@tokcalc/mcp-server@0.3.3
Runs install scripts—None
Networktokcalc.vercel.apptokcalc.vercel.app
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. #10.3.3latestOct 7, 2026