I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

greptile
Greptile MCP Server - Multi-Context Protocol Server for Greptile
3 years
Works with Finder
1
Github Watches
0
Github Forks
0
Github Stars
Greptile MCP Server
A WebSocket-based server that enables real-time code search and indexing capabilities across multiple repositories. It acts as a middleware between clients and the Greptile API, providing enhanced functionality for managing multiple search contexts and streaming results.
Features
- 🔌 WebSocket Server: Real-time communication with connection management and heartbeat mechanism
- 👥 Agent Management: Create and manage agent instances for different repositories
- 🔍 Repository Integration: Support repository indexing through Greptile API
- 🔎 Query Processing: Process and validate search queries with streaming results
- 🔐 Security: Secure WebSocket connections with API key authentication
- ⚙️ Configuration: Environment-based configuration with custom API endpoints
- 📊 Monitoring: Comprehensive logging system with performance metrics
- 📚 Client SDK: WebSocket client implementation with connection management
Installation
# Clone the repository
git clone https://github.com/yourusername/greptile-mcp.git
# Install dependencies
npm install
# Set up environment variables
cp .env.example .env
# Edit .env with your configuration
# Start the server
npm start
Environment Variables
# Server Configuration
PORT=3000
HOST=0.0.0.0
NODE_ENV=production
# Greptile API Configuration
GREPTILE_API_KEY=your-api-key
GITHUB_TOKEN=your-github-token
GREPTILE_BASE_URL=https://api.greptile.com/v2
# Authentication Configuration
AUTH_ENABLED=false
API_KEY=your-api-key-here
TOKEN_HEADER_NAME=X-API-Key
# Rate Limiting Configuration
RATE_LIMIT_ENABLED=true
RATE_LIMIT_WINDOW_MS=900000
RATE_LIMIT_MAX=100
# Logging Configuration
LOG_LEVEL=info
LOG_FORMAT=combined
Usage
Creating an Agent
curl -X POST http://localhost:3000/api/agents \
-H "Content-Type: application/json" \
-d '{
"name": "Demo Agent",
"description": "Testing agent",
"repositoryUrl": "https://github.com/facebook/react",
"branch": "main"
}'
WebSocket Connection
import WebSocket from 'ws';
const ws = new WebSocket('ws://localhost:3000');
const agentId = 'your-agent-id';
ws.on('open', () => {
// Register the connection
ws.send(JSON.stringify({
type: 'register',
agentId: agentId
}));
});
ws.on('message', (data) => {
const message = JSON.parse(data.toString());
console.log('Received:', message);
});
Querying Code
// After registration
ws.send(JSON.stringify({
type: 'query',
query: 'Find function main',
options: {
stream: true,
maxResults: 5,
includeContext: true
}
}));
Development
# Run in development mode
npm run dev
# Run tests
npm test
# Run linting
npm run lint
# Build for production
npm run build
Testing
The project includes comprehensive tests:
# Run all tests
npm test
# Run specific test file
npm test -- tests/server.test.js
# Run with coverage
npm run test:coverage
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Greptile API for providing the core search functionality
- ws for the WebSocket implementation
- All contributors who have helped with the project
相关推荐
Converts Figma frames into front-end code for various mobile frameworks.
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.
Delivers concise Python code and interprets non-English comments
Advanced software engineer GPT that excels through nailing the basics.
💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
MCP server to provide Figma layout information to AI coding agents like Cursor
Reviews

user_rBcOGVIp
I've been using Greptile by sosacrazy126 for a while now, and it has completely transformed the way I handle my projects. The tool is incredibly efficient and user-friendly, making data manipulation a breeze. Highly recommend checking it out on GitHub!