Bocha Search

v1.0.0Search & Data Extractionstable

An AI-focused search engine that enables AI applications to access high-quality knowledge from billions of webpages and ecosystem content sources across various domains including weather, news, encyclopedia, medical information, train tickets, and im

bocha-search-mcpmcpai-integration
Share:
162
Stars
0
Downloads
0
Weekly
0/5

What is Bocha Search?

Bocha Search is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-focused search engine that enables ai applications to access high-quality knowledge from billions of webpages and ecosystem content sources across various domains including weather, news, encyclope...

An AI-focused search engine that enables AI applications to access high-quality knowledge from billions of webpages and ecosystem content sources across various domains including weather, news, encyclopedia, medical information, train tickets, and im

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An AI-focused search engine that enables AI applications to

Use Cases

An AI-focused search engine that enables AI applications to access high-quality
BochaAI

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx bocha-search-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Bocha Search

Bocha Search MCP is an AI-focused search engine MCP server that gives AI applications access to high-quality web knowledge from nearly 10 billion webpages and structured content sources across domains including weather, news, encyclopedias, medical information, train schedules, and more. It exposes two tools — a general web search and an AI Search that returns structured semantic cards (weather cards, stock prices, encyclopedias, etc.) alongside web results. It is widely used in China as a Bing Search API alternative and serves as the official web search backend for DeepSeek and applications recommended by Alibaba, Tencent, and ByteDance.

Prerequisites

  • Python 3.10 or later with uv package manager installed
  • A Bocha AI API key obtained from https://open.bochaai.com
  • An MCP-compatible client such as Claude Desktop, Cursor, or a Python-based MCP client
1

Get a Bocha API key

Register and log in at the Bocha AI open platform (https://open.bochaai.com) to obtain your API key. The key begins with 'sk-'.

2

Clone the repository

Clone the Bocha Search MCP repository to your local machine.

git clone https://github.com/BochaAI/bocha-search-mcp.git
cd bocha-search-mcp
3

Configure your MCP client

Add the Bocha Search MCP server to your claude_desktop_config.json. On macOS, the config is at ~/Library/Application Support/Claude/claude_desktop_config.json. Replace /path/to/bocha-search-mcp with the actual clone path.

{
  "mcpServers": {
    "bocha-search-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/bocha-search-mcp",
        "run",
        "bocha-search-mcp"
      ],
      "env": {
        "BOCHA_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}
4

Restart your MCP client

Restart Claude Desktop or your MCP client to load the new server configuration. The Bocha Search tools should now appear as available MCP tools.

5

Test with the MCP Inspector (optional)

Use the MCP Inspector to debug and test the Bocha Search tools before using them in your AI client.

npx @modelcontextprotocol/inspector uv --directory /path/to/bocha-search-mcp run bocha-search-mcp

Bocha Search Examples

Client configuration

Claude Desktop configuration for the Bocha Search MCP server, using uv to run the Python server with the BOCHA_API_KEY environment variable.

{
  "mcpServers": {
    "bocha-search-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/yourname/bocha-search-mcp",
        "run",
        "bocha-search-mcp"
      ],
      "env": {
        "BOCHA_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}

Prompts to try

Example prompts using Bocha Web Search and Bocha AI Search, including queries that benefit from structured modal cards.

- "Search for the latest news about AI regulation in China"
- "What is the current weather in Shanghai?"
- "Search for information about the Alibaba 2024 ESG report and summarize the key points"
- "Find the train schedule from Beijing to Shanghai for tomorrow"
- "What is the current price of gold and how has it changed this week?"
- "Search for recent research papers on large language model safety"

Troubleshooting Bocha Search

Search returns an authentication error or 401 response

Verify your BOCHA_API_KEY is correct and starts with 'sk-'. Obtain a fresh key from https://open.bochaai.com if it has expired or been invalidated.

uv command not found when starting the MCP server

Install uv with 'pip install uv' or 'curl -LsSf https://astral.sh/uv/install.sh | sh'. Ensure the uv binary is on your system PATH and restart your MCP client after installation.

Bocha AI Search modal cards are not appearing in results

Modal cards (weather, stocks, encyclopedias) are only returned by the 'Bocha AI Search' tool, not the basic 'Bocha Web Search' tool. Make sure your agent is invoking the correct tool. Also note that some card types are only triggered by specific query patterns recognized by Bocha's semantic analysis.

Frequently Asked Questions about Bocha Search

What is Bocha Search?

Bocha Search is a Model Context Protocol (MCP) server that ai-focused search engine that enables ai applications to access high-quality knowledge from billions of webpages and ecosystem content sources across various domains including weather, news, encyclopedia, medical information, train tickets, and im It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Bocha Search?

Follow the installation instructions on the Bocha Search GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Bocha Search?

Bocha Search works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Bocha Search free to use?

Yes, Bocha Search is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "bocha-search-mcp": { "command": "npx", "args": ["-y", "bocha-search-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Bocha Search?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides