Bocha AI

Provides a web search MCP server for Bocha AI, returning web results and images with Markdown or JSON output.

javascript

6

GitHub Stars

javascript

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": {
    "yoko19191-bocha-ai-mcp-server": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/bocha-ai-mcp-server/build/index.js"
      ],
      "env": {
        "BOCHA_API_KEY": "YOUR_BOCHA_API_KEY"
      }
    }
  }
}

This MCP server provides Bocha AI web search capabilities as a self-contained service you can run locally or in your environment. It exposes a web-search tool that returns Chinese internet content and related images, and it can output results as human-friendly Markdown or structured JSON for programmatic use.

How to use

You interact with the Bocha AI web search MCP server through an MCP client. The core tool is bocha_web_search, which lets you search Chinese internet sources, optionally filter results by time, and choose whether to receive detailed summaries. You can request a specific number of results and decide if you want a Markdown human-readable output or a JSON payload for automation. In practice, you combine a query with optional parameters to tailor results to your needs.

Key tool: bocha_web_search

query: Search keywords (required)
freshness: Time range filter (OneDay, OneWeek, OneMonth, OneYear, noLimit)
summary: Enable detailed text summaries (true/false)
count: Number of results to return (1-50)
raw_json: Return format (true for JSON data, false for Markdown output)

How to install

Prerequisites: Node.js and npm must be installed on your system.

Step 1: Clone the MCP server repository and prepare the environment.

git clone git@github.com:yoko19191/bocha-ai-mcp-server.git
cd bocha-ai-mcp
cp .env.example .env

Step 2: Install dependencies and build the server.

npm install
npm run build

Configuration and running locally

The server is configured via an environment variable for the Bocha API key. You run the server locally with Node, pointing to the built entry script.

Example MCP configuration and run command are shown here so you can start the server in your environment.

{
  "mcpServers": {
    "bocha_ai_search": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/bocha-ai-mcp-server/build/index.js"
      ],
      "env": {
        "BOCHA_API_KEY": "<YOUR_BOCHA_API_KEY>"
      }
    }
  }
}

env BOCHA_API_KEY=YOUR_BOCHA_API_KEY node /ABSOLUTE/PATH/bocha-ai-mcp-server/build/index.js

Available tools

bocha_web_search

Web search tool that retrieves content from Chinese internet sources, with options for freshness, summaries, result count, and output format (Markdown or JSON).