tokcalc MCP Server MCP server
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Category: Dev tools
● Reachable, no MCP reply, checked 168 min ago · 995 ms
Source: official MCP Registry entry io.github.stevecrates489-commits/tokcalc · repository
Direct MCP URL and setup
CLAUDE CODE
claude mcp add --transport http io-github-stevecrates489-commits-tokcalc https://tokcalc.vercel.app/api/mcpCURSOR / VS CODE (mcp.json)
{ "mcpServers": { "io-github-stevecrates489-commits-tokcalc": { "url": "https://tokcalc.vercel.app/api/mcp" } } }