- Home
- MCP servers
- Baidu
Baidu
- python
18
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"evilran-baidu-mcp-server": {
"command": "uvx",
"args": [
"baidu-mcp-server"
]
}
}
}You can access Baidu-backed web search and content extraction through an MCP server that formats results for easy use with large language models. This server lets you perform searches, fetch page content, and get clean, model-friendly outputs with built-in rate limiting and error handling.
How to use
Use the MCP client you already have to connect to the Baidu Search MCP Server. You will run a local or remote MCP endpoint and issue search or fetch requests. Expect formatted results that include titles, URLs, and concise snippets suitable for feeding into an LLM.
How to install
Prerequisites you should have before installing: Node.js (for uv-based runtimes) or Python as needed by your environment. Ensure you have a runtime CLI capable of launching MCP servers.
Configuration and usage notes
The server is exposed as an MCP endpoint that can be run locally via a stdio command. The example configuration shows how Claude Desktop (or any MCP client) can start the server as a local process.
{
"mcpServers": {
"baidu-search": {
"command": "uvx",
"args": ["baidu-mcp-server"]
}
}
}
Troubleshooting and notes
If you encounter rate-limiting, rely on the built-in queue management and wait times. Check that your client configuration points to the correct MCP server and that the server process is running. Review logs for errors related to network access, parsing, or Baidu result formatting.
Available tools
Search Tool
Performs a web search on Baidu and returns a formatted list of results with titles, URLs, and snippets.
Content Fetching Tool
Fetches content from a webpage and returns cleaned, formatted text suitable for LLM consumption.