Skip to content
mcp/harbor
Verified official

inferbench MCP

v0.1.7

io.github.rudrendupaul/inferbench

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add inferbench -- uvx inferbench-cli

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.