Inference Aiops MCP server

official from AIops Tools Active last commit 6 d

{
  "mcpServers": {
    "aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ],
      "env": {
        "INFERENCE_AIOPS_MASTER_PASSWORD": "<inference_aiops_master_password>"
      }
    }
  }
}

{
  "mcpServers": {
    "aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ],
      "env": {
        "INFERENCE_AIOPS_MASTER_PASSWORD": "<inference_aiops_master_password>"
      }
    }
  }
}

{
  "mcpServers": {
    "aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ],
      "env": {
        "INFERENCE_AIOPS_MASTER_PASSWORD": "<inference_aiops_master_password>"
      }
    }
  }
}

{
  "servers": {
    "aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ],
      "env": {
        "INFERENCE_AIOPS_MASTER_PASSWORD": "${input:inference_aiops_master_password}"
      }
    }
  },
  "inputs": [
    {
      "id": "inference_aiops_master_password",
      "type": "promptString",
      "description": "Inference aiops master password",
      "password": true
    }
  ]
}

{
  "mcpServers": {
    "aiops-tools-inference-aiops": {
      "command": "uvx",
      "args": [
        "inference-aiops"
      ],
      "env": {
        "INFERENCE_AIOPS_MASTER_PASSWORD": "<inference_aiops_master_password>"
      }
    }
  }
}

file .mcp.json (in your project root)install uvx inference-aiopsversion 0.9.0

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

Before you enable it

An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.