{"servers":[{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.1.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.1.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-12T07:23:43.019166Z","publishedAt":"2026-07-12T07:23:43.019166Z","updatedAt":"2026-07-12T07:23:43.019166Z","isLatest":false}}},{"server":{"$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, 30 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.1.1","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.1.1","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-13T07:52:12.209893Z","publishedAt":"2026-07-13T07:52:12.209893Z","updatedAt":"2026-07-13T07:52:12.209893Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.10.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-12T00:58:43.088601Z","publishedAt":"2026-09-12T00:58:43.088601Z","updatedAt":"2026-09-12T00:58:43.088601Z","isLatest":false}}},{"server":{"$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":"0.10.1","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.1","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-12T09:46:07.82132Z","publishedAt":"2026-09-12T09:46:07.82132Z","updatedAt":"2026-09-12T09:46:07.82132Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.10.2","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.2","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-12T13:47:01.025745Z","publishedAt":"2026-09-12T13:47:01.025745Z","updatedAt":"2026-09-12T13:47:01.025745Z","isLatest":false}}},{"server":{"$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":"0.10.3","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.3","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-15T06:02:12.661663Z","publishedAt":"2026-09-15T06:02:12.661663Z","updatedAt":"2026-09-15T06:02:12.661663Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.10.4","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.10.4","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-09-16T23:25:58.077586Z","publishedAt":"2026-09-16T23:25:58.077586Z","updatedAt":"2026-09-16T23:25:58.077586Z","isLatest":false}}},{"server":{"$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":"0.11.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.11.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-10-15T06:54:13.529823Z","publishedAt":"2026-10-15T06:54:13.529823Z","updatedAt":"2026-10-15T06:54:13.529823Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.12.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.12.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-10-15T09:13:05.332475Z","publishedAt":"2026-10-15T09:13:05.332475Z","updatedAt":"2026-10-15T09:13:05.332475Z","isLatest":true}}},{"server":{"$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, 30 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.2.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.2.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-13T12:46:03.613158Z","publishedAt":"2026-07-13T12:46:03.613158Z","updatedAt":"2026-07-13T12:46:03.613158Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.2.1","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.2.1","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-16T15:10:40.544725Z","publishedAt":"2026-07-16T15:10:40.544725Z","updatedAt":"2026-07-16T15:10:40.544725Z","isLatest":false}}},{"server":{"$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, 30 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.3.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.3.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-17T05:43:34.356736Z","publishedAt":"2026-07-17T05:43:34.356736Z","updatedAt":"2026-07-17T05:43:34.356736Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 37 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.4.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.4.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-19T09:51:14.837865Z","publishedAt":"2026-07-19T09:51:14.837865Z","updatedAt":"2026-07-19T09:51:14.837865Z","isLatest":false}}},{"server":{"$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":"0.5.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.5.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-20T11:06:30.42613Z","publishedAt":"2026-07-20T11:06:30.42613Z","updatedAt":"2026-07-20T11:06:30.42613Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.6.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.6.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-07-21T09:41:08.792143Z","publishedAt":"2026-07-21T09:41:08.792143Z","updatedAt":"2026-07-21T09:41:08.792143Z","isLatest":false}}},{"server":{"$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":"0.7.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.7.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-08-02T09:27:02.193509Z","publishedAt":"2026-08-02T09:27:02.193509Z","updatedAt":"2026-08-02T09:27:02.193509Z","isLatest":false}}},{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.AIops-tools/inference-aiops","description":"Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.","title":"Inference AIops","repository":{"url":"https://github.com/AIops-tools/Inference-AIops","source":"github"},"version":"0.8.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.8.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-08-03T05:47:44.612162Z","publishedAt":"2026-08-03T05:47:44.612162Z","updatedAt":"2026-08-03T05:47:44.612162Z","isLatest":false}}},{"server":{"$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":"0.9.0","packages":[{"registryType":"pypi","identifier":"inference-aiops","version":"0.9.0","transport":{"type":"stdio"}}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-08-10T06:49:53.534042Z","publishedAt":"2026-08-10T06:49:53.534042Z","updatedAt":"2026-08-10T06:49:53.534042Z","isLatest":false}}}],"metadata":{"count":18}}