Baidu Search MCP server

This server implements the Model Context Protocol (MCP) for Baidu search, allowing AI assistants to perform intelligent searches using Baidu Wenxin API. It supports multiple models, provides search results with references, and offers features like deep search and recency filtering.

Installation

To get started with the Baidu Search MCP Server, install the required dependencies:

npm install @modelcontextprotocol/sdk axios

Configuration

Obtaining API Keys

Before using the server, you need to obtain API credentials from Baidu:

1. Visit Baidu Intelligent Cloud
2. Create an application and obtain your API key

Setting Environment Variables

Configure your API key as an environment variable:

export BAIDU_API_KEY=your_api_key_here

Usage

Running as a Standalone Server

You can run the server directly using Node.js:

node build/index.js

Integrating with MCP Configuration

Add the following configuration to your MCP settings file:

{
  "mcpServers": {
    "baidu-search": {
      "command": "node",
      "args": ["/path/to/baidu-search-mcp/build/index.js"],
      "env": {
        "BAIDU_API_KEY": "your_api_key_here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Search API

baidu_search

The search tool supports the following parameters:

• query (required): The search query text
• model: The model to use for search
  • Options: "ernie-3.5-8k", "ernie-4.0-8k", "deepseek-r1", "deepseek-v3"
  • Default: "ernie-3.5-8k"
• search_mode: Search mode setting
  • Options: "auto", "required", "disabled"
  • Default: "auto"
• enable_deep_search: Enable or disable deep search (default: false)
• search_recency_filter: Time range for search results
  • Options: "week", "month", "semiyear", "year"

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.