A
licenseNot graded
qualityD
maintenanceEnables AI assistants to perform intelligent web searches using the Baidu Wenxin API, supporting multiple models, search modes, and providing search results with reference sources.
48
6
MIT
bocha-ai-search
by yoko19191
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bocha-ai-searchsearch for latest tech news in China"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bocha AI Web Search MCP Server
An MCP (Model Context Protocol) server for Bocha AI web search functionality. This server provides a powerful search tool that returns web content and related images, supporting both human-readable Markdown output and raw JSON data.
About Bocha AI
Bocha AI (博查AI) is a legal and compliant AI search service operating in the People's Republic of China(PRC), specifically designed for searching Chinese internet content. It provides comprehensive search capabilities while adhering to all relevant Chinese regulations and standards.
Related MCP server: baidu-ai-search
Features
Web Search: Retrieve relevant web content, summaries, and images
Flexible Time Range: Search from the past day to unlimited time periods
Smart Summaries: Optional detailed text summaries
Dual Output Formats:
Markdown: Human-readable format with links and image previews
JSON: Structured data for programmatic processing
Robust Error Handling: Comprehensive error management with clear messages
Tools
bocha_web_search
A powerful web search tool that retrieves content from Chinese internet sources.
query(required): Search keywordsType: string
Description: The search terms to look up
freshness(optional): Time range for search resultsType: enum
Values: "OneDay", "OneWeek", "OneMonth", "OneYear", "noLimit"
Default: "noLimit"
Description: Filter results by time period
summary(optional): Enable detailed text summariesType: boolean
Default: false
Description: Whether to generate comprehensive summaries for search results
count(optional): Number of results to returnType: number
Range: 1-50
Default: 10
Description: Control the amount of search results
raw_json(optional): Return format controlType: boolean
Default: false
Description: When false, returns human-readable Markdown; when true, returns structured JSON data
Setup
make sure you have node.js and npm install already.
git clone git@github.com:yoko19191/bocha-ai-mcp-server.git
cd bocha-ai-mcp
cp .env.example .env # configure your bocha api key
npm install
npm run buildConfiguration
mcp.json
{
"mcpServers": {
"bocha-ai-search": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/bocha-ai-mcp-server/build/index.js"
],
"env": {
"BOCHA_API_KEY": "<YOUR_BOCHA_API_KEY>"
}
}
}
}cursor
env BOCHA_API_KEY=YOUR_BOCHA_API_KEY node /ABSOLUTE/PATH/bocha-ai-mcp-server/build/index.jsFURTURE_WORK
This project currently implements the Web Search API functionality of Bocha AI. Future updates will include support for:
AI Search: Advanced semantic search capabilities
Agent Search: Intelligent agent-based search features
License
MIT
Available Tools
1 toolbocha_web_searchA
使用 Bocha AI 进行网页搜索，搜索结果的详细信息，包括网页标题、网页URL、网页摘要、网站名称、网站Icon、网页发布时间等。支持 Markdown 格式的易读输出或原始 JSON 数据
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | 返回结果数量(default: 10) | |
| query | Yes | 搜索关键词 | |
| summary | No | 是否显示详细文本摘要(default: false) | |
| raw_json | No | 是否返回原始 JSON 数据而不是格式化的 Markdown(default: false) | |
| freshness | No | 搜索时间范围(default: noLimit) |
TDQS
A3.6/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the output content and available formats (Markdown vs raw JSON), which adds behavioral context. However, it omits details like rate limits, result ordering, error behavior, or authentication requirements, leaving notable gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the core purpose and then lists useful output details. It is succinct and avoids fluff, though it could be split into two sentences for better readability. Still efficient for the information conveyed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description must explain what the tool returns; it does enumerate result fields and output formats. However, it lacks information about result ordering, pagination, error handling, or any prerequisites, leaving the tool 'usable but not fully specified' for complex decisions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all five parameters with descriptions (100% coverage). The description adds no extra meaning beyond the schema, merely referencing the output format options already documented. Baseline 3 is appropriate given the schema's completeness.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs web search using Bocha AI and specifies the exact result fields (title, URL, snippet, site name, icon, publish time). It uses a specific verb+resource combination, making the tool's function unmistakable even without sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for web search needs but provides no explicit guidance on when to use this tool over alternatives or when not to use it. Since no alternatives are mentioned, the context is clear enough for a basic search tool, but exclusions and prerequisites are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
A3.9/5.0
Disambiguation5/5
Only one tool exists, so there is no ambiguity in tool selection. The single tool's purpose is clear.
Naming Consistency5/5
The tool name 'bocha_web_search' follows a consistent snake_case convention and clearly communicates its functionality, making it predictable.
Tool Count3/5
A single tool is borderline for a search server; it feels thin compared to typical search services that might offer multiple search types or additional utilities, but it is not excessive.
Completeness5/5
The web search tool fully covers the core search operation, including detailed result information and flexible output formats, with no obvious gaps in the provided domain.
Maintenance
ActivityInactive
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Baidu search results and Chinese SERP data via the Apify Baidu Search Scraper, hosted MCP.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
Related MCP Servers
- Apache 2.0
- AlicenseBqualityDmaintenanceProvides web search capabilities through Baidu with content fetching and parsing features, allowing LLMs to search the web and extract webpage content.128MIT
- AlicenseAqualityCmaintenanceProvides Bing Chinese search and webpage crawling tools, enabling AI assistants to fetch real-time web information without API keys.237468MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yoko19191/bocha-ai-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server