MCP Prow Server

A Model Context Protocol (MCP) server for interacting with Prow CI/CD systems, retrieving build logs, and diagnosing PR build issues.

Features

• 🔍 Job Management: Get latest job runs and retrieve job logs
• 📊 Build Analysis: Find builds for specific PRs and analyze results
• 🚀 Smart Discovery: Multi-strategy PR build finding with fallback mechanisms
• 🔧 Diagnostics: Comprehensive PR build status diagnosis and test failure extraction

Architecture Diagram

Available Tools

The server exposes 7 MCP tools:

1. get_latest_job_run - Get the latest job run information for a specific job name
2. get_job_logs - Retrieve logs for a specific Prow job ID
3. get_build_logs - Get logs for a specific build ID and job name
4. get_latest_prow_build_for_pr - Find the latest Prow build for a GitHub PR
5. get_prow_logs_from_pr - Get comprehensive logs for a specific PR
6. diagnose_pr_build_status - Comprehensive diagnostic tool for PR build issues
7. get_test_failures_from_artifacts - Extract test failures from build artifacts

Example Output

Check out the examples directory.

Quick Start

Installation

cd /path/to/prow-mcp-server
uv sync  # Creates venv and installs dependencies from uv.lock
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

MCP Configuration

Cursor IDE (stdio transport)

Add to your ~/.cursor/mcp.json:

{
  "mcpServers": {
    "prow": {
      "command": "uv",
      "args": ["run", "/path/to/prow-mcp-server/.venv/bin/python", "/path/to/prow-mcp-server/main.py"],
      "description": "MCP server for Prow CI/CD integration"
    }
  }
}

Web-based Integration (SSE transport)

For web applications or services that need HTTP-based communication:

{
  "mcpServers": {
    "prow": {
      "url": "http://0.0.0.0:8000/sse/",
      "description": "MCP server for Prow CI/CD integration with direct SSE",
      "env": {
        "MCP_TRANSPORT": "sse"
      }
    }
  }
}

SSE Endpoint: http://0.0.0.0:8000/sse/

Note: Make sure to start the SSE server separately with MCP_TRANSPORT=sse uv run main.py before using this configuration.

Testing

Run the comprehensive test suite (18 tests):

uv run python run_tests.py           # Recommended
uv run pytest tests/ -v              # Direct pytest

All tests pass in under 0.25 seconds with full coverage of utilities, services, and MCP tools.

Architecture

The server uses a modular architecture with clear separation of concerns:

mcp_server/
├── main.py          # Server entry point
├── config.py        # Configuration
├── models/          # Type definitions
├── utils/           # Helper functions
├── services/        # Business logic (Prow API, GCS)
└── tools/           # MCP tool implementations

Smart Build Discovery

The server uses intelligent fallback strategies to find PR builds:

1. Active Prow Jobs (real-time) →
2. GCS PR Logs (archived) →
3. GCS Regular Logs (metadata scanning) →
4. Pattern-based Search (heuristic fallback)

Container Deployment

STDIO Transport (Default)

For standard MCP integration with Cursor IDE:

# Build
podman build -t prow-mcp:latest .

# Run
podman run -i --rm prow-mcp:latest

# MCP Config
{
  "mcpServers": {
    "prow-server": {
      "command": "podman",
      "args": ["run", "-i", "--rm", "localhost/prow-mcp:latest"]
    }
  }
}

SSE Transport

For web-based integrations and HTTP communication:

# Build SSE container
podman build -f Containerfile.sse -t prow-mcp-sse:latest .

# Run SSE container
podman run -p 8000:8000 --rm prow-mcp-sse:latest

# MCP Config
{
  "mcpServers": {
    "prow-sse": {

... [View full README on GitHub](https://github.com/redhat-community-ai-tools/prow-mcp-server#readme)