Baidu MCP Server

🚀 Baidu Search MCP Server

A Model Context Protocol (MCP) server that provides Baidu search functionality, with additional features for content retrieval and parsing.

🚀 Quick Start

This is a Model Context Protocol (MCP) server that offers Baidu search functionality, along with additional capabilities for content retrieval and parsing.

✨ Features

• Web Search: Conduct advanced rate-limited and formatted searches on Baidu.
• Content Retrieval: Retrieve and parse web page content with intelligent text extraction.
• Rate Limiting: Built-in protection mechanisms for search and content retrieval.
• Error Handling: Comprehensive error handling and logging.
• LLM-Friendly Output Format: Results formatted specifically for large language models.

📦 Installation

Install via Smithery

Use Smithery to automatically install the Baidu search server for Claude Desktop:

npx -y @smithery/cli install @Evilran/baidu-mcp-server --client claude

Install via uv

Install directly from PyPI using uv:

uv pip install baidu-mcp-server

💻 Usage Examples

Configure Claude Desktop

1. Download Claude Desktop.
2. Create or edit your Claude Desktop configuration file:
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following configuration:

{
    "mcpServers": {
        "baidu-search": {
            "command": "uvx",
            "args": ["baidu-mcp-server"]
        }
    }
}

3. Restart Claude Desktop.

Development

For local development, you can use the MCP CLI:

# Run with MCP Inspector
mcp dev server.py

# Install to the local environment for testing
mcp install server.py

Basic Usage

1. Search Tool

async def search(query: str, max_results: int = 10) -> str

Perform a web search on Baidu and return formatted results.

Parameters:

• query: The search query string.
• max_results: The maximum number of results to return (default: 10).

Returns: A formatted string containing titles, links, and snippets.

2. Content Retrieval Tool

async def fetch_content(url: str) -> str

Fetch and parse web page content.

Parameters:

• url: The URL of the web page to fetch content from.

Returns: Cleaned and formatted text content.

📚 Documentation

Rate Limiting

• Search: Maximum of 30 requests per minute.
• Content Retrieval: Maximum of 20 requests per minute.
• Automatic queue management and waiting time.

Result Processing

• Remove ads and irrelevant content.
• Clean Baidu redirect links.
• Format results to optimize the experience for large language models.
• Appropriately truncate long text.

Error Handling

• Comprehensive error capture and reporting.
• Detailed logging through the MCP context.
• Graceful degradation in case of rate limits or timeouts.

🔧 Contribution

Issues and pull requests are welcome! Here are some potential areas for improvement:

• Add more search parameters (region, language, etc.).
• Enhance content parsing options.
• Add a cache layer for commonly used content.
• Implement additional rate-limiting strategies.

📄 License

This project is open-source under the MIT License.

🙏 Acknowledgments

Thanks to @Evilran for their contributions to this project.