{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.10.2","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.2","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-12T13:47:01.025745Z","publishedAt":"2026-09-12T13:47:01.025745Z","updatedAt":"2026-09-12T13:47:01.025745Z","isLatest":true}}}