{"id":"49020455-4c47-4045-9793-7948afc3fc18","slug":"vibechecker","kind":"mcp","name":"Vibechecker","summary":"Production-ready multi-agent MCP server for automated code analysis and documentation generation. Built with FastMCP for seamless AI tool integration, featuring specialized agents for issue detection,","owner":"Arpit-Moga","repoUrl":"https://github.com/Arpit-Moga/Vibechecker","license":"MIT","licenseTier":"permissive","trust":"community","stars":2,"match":null,"fewStars":true,"format":"mcp","createdAt":"2025-07-26T10:08:59.000Z","addedAt":"2026-10-21T15:37:08.539Z","logoUrl":"https://avatars.githubusercontent.com/u/45970708?u=3c193b6dff695ba8dbb1dcf421e3f0cabd6159c1&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["writing","developer-tools","cloud-infra"],"tags":[],"runtime":"python","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-23T11:02:11.649Z","sample":false,"url":"https://conduits.dev/tools/vibechecker","language":"Python","transports":["stdio"],"install":{"pypi":"multiagent-mcp-server"},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Multi-Agent MCP Server\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![MCP](https://img.shields.io/badge/MCP-2024--11--05-blue.svg)](https://modelcontextprotocol.io/)\n[![Smithery](https://img.shields.io/badge/Smithery-Compatible-green.svg)](https://smithery.ai/)\n\nA production-ready, modular multi-agent MCP server for automated codebase review and documentation generation. Built with the Model Context Protocol (MCP) for seamless integration with AI development workflows and compatible with Smithery for easy deployment.\n\n## 🚀 Features\n\n- **🤖 Multi-Agent Architecture**: Specialized AI agents for different analysis types\n  - **Debt Agent**: Technical debt and maintainability analysis\n  - **Improvement Agent**: Code quality improvement recommendations\n  - **Critical Agent**: Security vulnerabilities and reliability issues\n  - **Documentation Agent**: Comprehensive project documentation generation\n- **📡 MCP Integration**: Full Model Context Protocol support for AI tool integration\n- **🔀 Workflow Orchestration**: Advanced DSPy workflow integration for intelligent analysis\n- **✅ Strict Validation**: Comprehensive output validation with Pydantic schemas\n- **🏭 Production Ready**: Comprehensive testing, logging, and professional packaging\n- **☁️ Smithery Compatible**: Ready for deployment on Smithery platform\n- **⚡ Flexible Execution**: Quick scan for fast analysis or deep scan with LLM integration\n\n## 📋 Table of Contents\n\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [MCP Tools Reference](#mcp-tools-reference)\n- [Smithery Integration](#smithery-integration)\n- [Configuration](#configuration)\n- [API Documentation](#api-documentation)\n- [Development](#development)\n- [Contributing](#contributing)\n- [License](#license)\n\n## 🛠️ Installation\n\n### Via Smithery (Recommended)\n\nThe easiest way to use this MCP server is through [Smithery](https://smithery.ai/):\n\n1. Visit [Smithery](https://smithery.ai/)\n2. Search for \"multi-agent-code-review\"\n3. Add to your AI workflow with one click\n\n### Python Package\n\n```bash\n# Using uv (recommended)\nuv add multiagent-mcp-server\n\n# Using pip\npip install multiagent-mcp-server\n\n# Using conda\nconda install -c conda-forge multiagent-mcp-server\n```\n\n### From Source\n\n```bash\n# Clone the repository\ngit clone https://github.com/Arpit-Moga/Vibechecker.git\ncd Vibechecker\n\n# Install with uv (recommended)\nuv sync\n\n# Or with pip\npip install -e .\n```\n\n## 🚀 Quick Start\n\n### As MCP Server\n\n```bash\n# Run the MCP server\npython -m multiagent_mcp_server\n\n# Or using the installed script\nmultiagent-mcp-server\n```\n\n### MCP Client Configuration\n\nAdd to your MCP client configuration (e.g., Claude Desktop, Continue, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"multi-agent-code-review\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"multiagent_mcp_server\"],\n      \"env\": {\n        \"CODE_DIRECTORY\": \"./\",\n        \"LOG_LEVEL\": \"INFO\"\n      }\n    }\n  }\n}\n```\n\n### With Environment Variables\n\n```bash\n# Set API keys for LLM analysis (optional for quick mode)\nexport GOOGLE_API_KEY=\"your-google-api-key\"\nexport OPENAI_API_KEY=\"your-openai-api-key\"\n\n# Configure analysis settings\nexport CODE_DIRECTORY=\"/path/to/your/project\"\nexport MAX_FILE_SIZE_MB=\"10.0\"\nexport LOG_LEVEL=\"INFO\"\n\n# Run the server\npython -m multiagent_mcp_server\n```\n\n## 🔧 MCP Tools Reference\n\nThe server provides the following MCP tools for AI agents:\n\n### `issue_detection_review`\nRuns unified issue detection analysis on the specified code directory.\n\n**Parameters:**\n- `code_directory` (string, optional): Path to analyze (default: current directory)\n- `output_directory` (string, optional): Output path (default: ./DOCUMENTATION)\n- `output_format` (enum): \"md\" or \"json\" (default: \"md\")\n- `scan_mode` (enum): \"quick\" or \"deep\" (default: \"quick\")\n\n**Example:**\n```json\n{\n  \"tool\": \"issue_detection_review\",\n  \"arguments\": {\n    \"code_directory\": \"./src\",\n    \"scan_mode\": \"deep\",\n    \"output_format\": \"json\"\n  }\n}\n```\n\n### `documentation_generate`\nGenerates comprehensive project documentation.\n\n**Parameters:**\n- `code_directory` (string, optional): Path to analyze\n- `output_directory` (string, optional): Output path\n\n### `comprehensive_review`\nRuns all analyses in a coordinated workflow for complete project review.\n\n**Parameters:** Same as `issue_detection_review`\n\n## ☁️ Smithery Integration\n\nThis MCP server is fully compatible with [Smithery](https://smithery.ai/), providing:\n\n- **Easy Deployment**: One-click deployment to Smithery cloud\n- **Automatic Discovery**: Server is automatically indexed in Smithery registry\n- **Configuration Schema**: Full JSON schema validation for parameters\n- **HTTP Transport**: Optional HTTP endpoint for remote access\n- **Security Scanning**: Passes Smithery security validation\n\n### Smithery Configuration\n\nThe server includes a `smithery.yaml` configuration file that defines:\n- Server metadata and capabilities\n- Connection methods (stdio and HTTP)\n- Tool schemas and validation\n- Security settings\n\n### Publishing to Smithery\n\n1. Ensure your code is in a public GitHub repository\n2. Add proper tags and description in `smithery.yaml`\n3. Smithery will automatically discover and index your server\n4. Users can then find and use your server through the Smithery platform\n\n## ⚙️ Configuration\n\n### Environment Variables\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `CODE_DIRECTORY` | Default directory to analyze | `.` |\n| `GOOGLE_API_KEY` | Google AI API key for LLM analysis | None |\n| `OPENAI_API_KEY` | OpenAI API key for LLM analysis | None |\n| `MAX_FILE_SIZE_MB` | Maximum file size to process | `5.0` |\n| `MAX_FILES_TO_PROCESS` | Maximum number of files | `100` |\n| `LOG_LEVEL` | Logging level | `INFO` |\n\n### Scan Modes\n\n- **Quick Mode**: Fast static analysis using linting tools (ruff, bandit, mypy)\n- **Deep Mode**: Comprehensive analysis including LLM-powered review\n\n### Output Formats\n\n- **Markdown**: Human-readable reports with formatting\n- **JSON**: Structured data for programmatic consumption\n\n## 📚 API Documentation\n\n### Response Format\n\nAll tools return a consistent response structure:\n\n```typescript\ninterface AgentReport {\n  issues: IssueOutput[];\n  review: string;\n  total_issues?: number;\n  high_severity_count?: number;\n  documentation_files?: number;\n  error?: boolean;\n}\n\ninterface IssueOutput {\n  type: \"maintainability\" | \"security\" | \"performance\" | \"compliance\" | \"other\";\n  severity: \"low\" | \"medium\" | \"high\";\n  description: string;\n  file: string;\n  line: number;\n  suggestion?: string;        // For maintainability/performance\n  remediation?: string;       // For security/compliance\n  reference?: string;\n}\n```\n\n### Error Handling\n\nThe server implements comprehensive error handling:\n- Input validation with detailed error messages\n- Graceful degradation when tools are unavailable\n- Structured error responses with error codes\n- Comprehensive logging for debugging\n\n## 🧪 Development\n\n### Prerequisites\n\n- Python 3.10+\n- uv package manager (recommended) or pip\n\n### Setup Development Environment\n\n```bash\n# Clone the repository\ngit clone https://github.com/Arpit-Moga/Vibechecker.git\ncd Vibechecker\n\n# Install development dependencies\nuv sync --dev\n\n# Install pre-commit hooks\npre-commit install\n```\n\n### Running Tests\n\n```bash\n# Run all tests\npytest\n\n# Run with coverage\npytest --cov=multiagent_mcp_server\n\n# Run specific test file\npytest tests/test_models.py -v\n```\n\n### Code Quality\n\n```bash\n# Format code\nblack src tests\nisort src tests\n\n# Lint code\nflake8 src tests\nmypy src\n\n# Security scan\nbandit -r src\n```\n\n### Project Structure\n\n```\nmultiagent-mcp-server/\n├── src/multiagent_mcp_server/    # Main package\n│   ├── __init__.py               # Package exports\n│   ├── __main__.py               # Module entry point\n│   ├── server.py                 # MCP server implementation\n│   ├── models.py                 # Pydantic models\n│   ├── config.py                 # Configuration management\n│   ├── base_agent.py             # Base agent class\n│   ├── issue_detection_agent.py  # Issue detection logic\n│   ├── documentation_agent.py    # Documentation generation\n│   └── ...                       # Other modules\n├── tests/                        # Test suite\n├── docs/                         # Documentation\n├── smithery.yaml                 # Smithery configuration\n├── mcp.json                      # MCP manifest\n├── pyproject.toml                # Package configuration\n└── README.md                     # This file\n```\n\n## 🤝 Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n### Quick Contribution Steps\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Make your changes\n4. Add tests for new functionality\n5. Ensure all tests pass (`pytest`)\n6. Commit your changes (`git commit -m 'Add amazing feature'`)\n7. Push to the branch (`git push origin feature/amazing-feature`)\n8. Open a Pull Request\n\n### Development Guidelines\n\n- Follow PEP 8 style guidelines\n- Add type hints to all functions\n- Write comprehensive tests for new features\n- Update documentation as needed\n- Ensure backwards compatibility\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- [Model Context Protocol](https://modelcontextprotocol.io/) for the excellent protocol specification\n- [Smithery](https://smithery.ai/) for the amazing MCP server registry and deployment platform\n- [FastMCP](https://github.com/jlowin/fastmcp) for the simplified MCP server framework\n- [DSPy](https://dspy-docs.vercel.app/) for advanced workflow orchestration\n- All contributors and the open-source community\n\n## 🔗 Links\n\n- **GitHub Repository**: https://github.com/Arpit-Moga/Vibechecker\n- **Smithery Registry**: https://smithery.ai/\n- **Model Context Protocol**: https://modelcontextprotocol.io/\n- **Documentation**: https://github.com/Arpit-Moga/Vibechecker/tree/main/docs\n- **Issue Tracker**: https://github.com/Arpit-Moga/Vibechecker/issues\n\n---\n\n**Ready to supercharge your code review process? Try the Multi-Agent MCP Server today!** 🚀\n\n## 🚦 Quick Start\n\n### Start the Server\n\n```bash\n# Using the installed package\nmultiagent-mcp-server\n\n# Or using Python module\npython -m multiagent_mcp_server.server\n```\n\n## 🧩 MCP Tools Reference\n\nThe server exposes agent tools via the Model Context Protocol (MCP), not RESTful HTTP endpoints.\n\n### Available MCP Tools\n\n| Tool Name                  | Description                                      |\n|----------------------------|--------------------------------------------------|\n| `issue_detection_review`   | Unified code issue detection and analysis         |\n| `documentation_generate`   | Generate comprehensive project documentation      |\n| `comprehensive_review`     | Run all agents for complete codebase analysis     |\n\nRefer to the MCP documentation for integration details.\n\n## 📖 Documentation\n\nComprehensive documentation is available in the [`docs/`](docs/) directory:\n\n- **[Getting Started Guide](docs/guides/getting_started.md)** - Quick start tutorial\n- **[Architecture Guide](docs/development/architecture.md)** - System architecture overview\n- **[Development Guide](docs/development/)** - Development setup and guidelines\n- **[Agent Documentation](docs/phases/)** - Agent-specific documentation\n\n## 🏗️ System Architecture\n\n```mermaid\nflowchart TD\n    subgraph Agents\n        A1[Documentation Agent]\n        A2[Unified Issue Detection Agent]\n    end\n    subgraph Plugins\n        P1[Bandit Plugin]\n        P2[Mypy Plugin]\n        P3[Ruff Plugin]\n        P4[Semgrep Plugin]\n    end\n    U[User/Client] --> S[MCP Server]\n    S --> Agents\n    S --> Plugins\n    Agents --> R[Aggregated Report]\n    Plugins --> R\n    R --> U\n```\n\n## 🔧 Development\n\n### Prerequisites\n\n- Python 3.10 or higher\n- uv or pip for package management\n\n### Setup\n\n```bash\n# Clone and setup\ngit clone https://github.com/your-org/multi-agent-mcp-server.git\ncd multi-agent-mcp-server\nuv sync\n\n# Install pre-commit hooks\npre-commit install\n\n# Run tests\npytest\n\n# Run with coverage\npytest --cov=src/multiagent_mcp_server\n```\n\n### Project Structure\n\n```\nmulti-agent-mcp-server/\n├── src/multiagent_mcp_server/    # Main package\n├── docs/                         # Documentation\n├── examples/                     # Usage examples\n├── tests/                        # Test suite\n├── data/                         # Sample data and outputs\n└── scripts/                      # Utility scripts\n```\n\n## 🤝 Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details on:\n\n- Development setup\n- Code style guidelines\n- Testing requirements\n- Pull request process\n\n### Quick Contribution Steps\n\n1. Fork the repository\n2. Create a feature branch\n3. Make your changes\n4. Add tests and documentation\n5. Submit a pull request\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- Built with the [Model Context Protocol](https://modelcontextprotocol.io/)\n- Powered by [DSPy](https://github.com/stanfordnlp/dspy)\n- Validation with [Pydantic](https://pydantic.dev/)\n\n---\n\n**[📚 Documentation](docs/)** • **[🐛 Issues](https://github.com/your-org/multi-agent-mcp-server/issues)** • **[💬 Discussions](https://github.com/your-org/multi-agent-mcp-server/discussions)**\n"}