Multi-Agent Dev Automation System — Agentic CI/CD Pipeline

An automated agentic CI/CD pipeline using FastAPI, Claude-powered agents, and Model Context Protocol (MCP) to automatically analyze GitHub Pull Requests, run unit tests, and lint files.

Project Architecture

devagent/
├── agents/             # Claude-powered agents
│   ├── base_agent.py      # Base agent with tool execution loop
│   ├── reviewer_agent.py  # Reviewer agent parsing PR diffs
│   └── prompts.py         # System prompts
├── app/                # FastAPI application
│   ├── api/routes/        # API endpoints (health)
│   ├── services/          # Claude integration service
│   ├── config.py          # Settings and environment config
│   └── main.py            # FastAPI main entrypoint
├── mcp_server/         # MCP Server
│   ├── server.py          # MCPServer registration and endpoints
│   └── tools/             # MCP tools (fetch_pr_diff, lint, run_tests, search)
├── tests/              # Test suite (pytest)
│   ├── test_agents.py
│   ├── test_health.py
│   └── test_mcp_tools.py
├── .env.example        # Environment template
├── .gitignore          # Git ignore files
└── requirements.txt    # Python dependencies

Related MCP server: code-review-mcp-server

Features & MCP Tools

• BaseAgent: Executes a tool-calling loop using the Anthropic API (Claude 3.5 Sonnet) to recursively gather codebase information.

• ReviewerAgent: Performs code reviews on PR diffs looking for correctness bugs, security vulnerabilities, and code quality issues.

• MCP Tools:

  • fetch_pr_diff: Retrieves changed files and patches for a GitHub PR.

  • search_codebase: Searches local files using patterns or text search.

  • run_tests: Runs unit tests using pytest within the target repository.

  • lint_code: Runs Ruff linter on target files.

Installation & Setup

1. Clone the repository (once pushed to GitHub).

2. Create and activate a virtual environment:

   python -m venv .venv
   # Windows:
   .venv\Scripts\activate
   # Linux/macOS:
   source .venv/bin/activate

3. Install dependencies:

   pip install -r requirements.txt

4. Configure environment variables: Create a .env file from the template and fill in your keys:

   cp .env.example .env

   Add your ANTHROPIC_API_KEY and optionally GITHUB_TOKEN.

Running the Project

Running FastAPI App

uvicorn app.main:app --reload

Access the API docs at http://localhost:8000/docs.

Running MCP Server

To run the MCP server directly:

python mcp_server/server.py

Running Tests

To run all tests and verify the system works:

python -m pytest