incident_investigation_MCP_Server_Harness

Sput/incident_investigation_MCP_Server_Harness
★ 0 stars Python AI/LLM Updated 2d ago
An MCP server.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "incident_investigati": {
      "command": "uvx",
      "args": [
        "incident-investigation-mcp-server-harness"
      ]
    }
  }
}

Or install with pip: pip install incident-investigation-mcp-server-harness

README Excerpt

AI Incident Investigator is a portfolio project that demonstrates production-grade AI engineering through multi-agent orchestration, custom MCP tool integration, and end-to-end AI observability. The canonical demo investigates a synthetic database connection exhaustion incident. A FastAPI backend runs a LangGraph supervisor workflow, gathers operational evidence through a custom MCP server backed by local JSON fixtures, challenges unsupported conclusions with a reliability reviewer, and stores t