Jina AI Search MCP Server
A Model Context Protocol server implementation that provides a standardized interface for interacting with Jina AI's Reader and Search APIs.
README
Jina AI Search MCP Server
🚀 Quick Start: Try it instantly with Claude Desktop using our hosted endpoint:
https://jina-mcp.onrender.com/sse
A powerful Model Context Protocol (MCP) server implementation that provides seamless access to Jina AI's Search Foundation API. This server enables AI assistants and applications to leverage Jina's advanced search, reading, and knowledge retrieval capabilities through a standardized MCP interface.
📋 Table of Contents
- ✨ Features
- 🔧 How it Works
- ⚡ Quick Start
- 📦 Installation
- ⚙️ Configuration
- 🔌 MCP Server Setup
- 💡 Usage Examples
- 📚 API Documentation
- 🛠️ Development
- 🤝 Contributing
- 💬 Support
- 📄 License
✨ Features
- 🚀 MCP-compliant server implementation - Full compatibility with Model Context Protocol
- 🔍 Jina AI Search & Reader APIs - Access to powerful AI search and content reading capabilities
- 📚 DeepWiki Integration - Enhanced Wikipedia access with AI understanding
- 🏗️ Clean, modular codebase - Well-structured and maintainable architecture
- 📖 Comprehensive documentation - Detailed guides and API references
- ⚡ Easy setup - Simple installation with virtual environment support
- 🔐 Secure authentication - OAuth2 Bearer token support
- 🌐 Real-time processing - Server-Sent Events (SSE) for live communication
🔧 How it Works
The Jina MCP server provides seamless integration with Jina AI's powerful search and reading capabilities through the Model Context Protocol. Here's how you can leverage its features:
🔍 Search with Jina AI
Ask questions and get comprehensive search results from across the web:
"Search for the latest developments in artificial intelligence"
"Find information about sustainable energy solutions"
"What are the recent breakthroughs in quantum computing?"
🎯 Use Cases
- Research assistance - Get comprehensive information on any topic
- Content analysis - Read and analyze web pages
- Knowledge discovery - Explore Wikipedia with AI-enhanced understanding
- AI assistant integration - Seamlessly integrate with Claude Desktop and other MCP clients
⚡ Quick Start
Prerequisites
- Python 3.8+
- pip package manager
- Jina AI API Key (Get yours here)
Instant Setup with Claude Desktop
Add this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"jina": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"supergateway",
"--sse",
"https://jina-mcp.onrender.com/sse",
"--oauth2Bearer=your-jina-api-key"
]
}
}
}
Replace your-jina-api-key with your actual Jina AI API key and restart Claude Desktop!
📦 Installation
1. Clone the Repository
git clone https://github.com/Meetpatel006/jina-mcp.git
cd jina-mcp
2. Set Up Virtual Environment
# Create virtual environment
python -m venv venv
# Activate virtual environment
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate
3. Install Dependencies
pip install -r requirements.txt
⚙️ Configuration
Environment Setup
Create a .env file in the project root:
JINA_API_KEY=your_jina_api_key_here
Running the Server Locally
python -m jina_mcp.server
🔌 MCP Server Setup
For Claude Desktop (Recommended)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"jina": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"supergateway",
"--sse",
"https://jina-mcp.onrender.com/sse",
"--oauth2Bearer=your-jina-api-key"
]
}
}
}
Local Development Setup
For local development:
{
"mcpServers": {
"jina": {
"command": "python",
"args": ["-m", "jina_mcp.server"],
"cwd": "/path/to/jina-mcp",
"env": {
"JINA_API_KEY": "your-api-key-here"
}
}
}
}
Configuration Steps
- For Claude Desktop: Add the configuration to your
claude_desktop_config.jsonfile - Replace API Key: Use your actual Jina AI API key
- Restart Client: Restart your MCP client to load the new server
💡 Usage Examples
Basic Search
# Search for information
"Search for Python best practices"
"Find the latest news about AI development"
DeepWiki Queries
# Ask deepwiki for detailed information
"Ask deepwiki about machine learning"
"Ask deepwiki to explain neural networks"
"Ask deepwiki about the Python programming language"
Web Content Analysis
# Read and analyze web content
"Read https://example.com/blog-post"
"Summarize the content from https://research-paper-url.com"
📚 API Documentation
Documentation Resources
- 📖 API Documentation - Complete API reference
- 🔧 MCP Protocol Documentation - MCP implementation details
- 🐍 Python SDK Documentation - Python SDK usage
- 🔍 Jina API Documentation - Jina AI API reference
Code Examples
Explore the examples directory:
- 🔧 Client Example - Basic client implementation
- More examples coming soon!
🛠️ Development
Development Setup
# Install development dependencies
pip install -r requirements-dev.txt
# Run tests
pytest
# Code formatting
black .
# Linting
flake8 .
Project Structure
jina-mcp/
├── jina_mcp/ # Main package
│ ├── __init__.py
│ ├── server.py # MCP server implementation
│ ├── client.py # Jina API client
│ ├── config.py # Configuration management
│ ├── models.py # Data models
│ └── tools.py # MCP tools
├── docs/ # Documentation
├── examples/ # Usage examples
├── requirements.txt # Dependencies
└── README.md # This file
🤝 Contributing
We welcome contributions! Here's how you can help:
How to Contribute
- Fork the repository
- Create a 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
Contribution Guidelines
- Follow the existing code style (use
blackfor formatting) - Add tests for new features
- Update documentation as needed
- Ensure all tests pass before submitting
💬 Support
Get Help
- 📖 Documentation - Comprehensive guides and references
- 🐛 Issue Tracker - Report bugs or request features
- 💬 Discussions - Community discussions
- 📧 Contact: Create an issue for support
Useful Links
<div align="center">
Made with ❤️ by Meet Patel
⭐ Star this repo if you find it helpful! ⭐
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。