Observability AIops

Overview

Observability AIops is a Model Context Protocol (MCP) server: Governed Prometheus + Grafana ops: PromQL, alerts, dashboards, RCA; 39 tools. In practice that means any MCP-compatible AI assistant can call Observability AIops's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package observability-aiops (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.9.0, published under the MIT license, with source at AIops-tools/Observability-AIops on GitHub.

Observability AIops is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Observability AIops for AIops-tools, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "observability_aiops": {
      "command": "uvx",
      "args": [
        "observability-aiops"
      ]
    }
  }
}