# tokcalc MCP Server

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

- Weekly downloads: 337
- GitHub stars: 1
- Health: active
- Repository: https://github.com/stevecrates489-commits/tokcalc
- Registry names: io.github.stevecrates489-commits/tokcalc
- Categories: Dev tools & GitHub, Cloud & infrastructure, AI models & media
- Snapshot: 2026-10-29

## Install

```sh
npx -y @tokcalc/mcp-server
```

```json
{
  "mcpServers": {
    "tokcalc-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@tokcalc/mcp-server"
      ]
    }
  }
}
```

Source: https://mcpmorning.com/mcp/stevecrates489-commits-tokcalc/

## Transport

stdio, remote