AgentUni

Inference AIops

by @AIops-tools / v0.10.4

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

Install

PyPI / stdio

uvx inference-aiops

Client config (Claude Desktop, Cursor, Windsurf and most MCP clients)

{
  "mcpServers": {
    "io-github-aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ]
    }
  }
}

Source: official MCP Registry record · registry name io.github.AIops-tools/inference-aiops · published 2026-09-16 · updated 2026-09-16. Not an endorsement; review the code before connecting it to anything sensitive.

Similar

More AI Models & Agents servers

Browse category