# tokcalc MCP Server

- Registry name: `io.github.stevecrates489-commits/tokcalc` · version 0.3.3
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: —
- Declared risk: Unknown (tools not visible)
- Capabilities (declared by the server): -
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.stevecrates489-commits%2Ftokcalc
- Server page: https://mcpstation.net/s/io.github.stevecrates489-commits--tokcalc.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://tokcalc.vercel.app/api/mcp`

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html