Skip to content
mcp/harbor
Verified official

Inference AIops MCP

v0.10.4

io.github.aiops-tools/inference-aiops

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add inference-aiops -- uvx inference-aiops

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.