智谱 Web Search MCP 工具(STDIO)
@cr-zhichen
About 智谱 Web Search MCP 工具(STDIO)
一个通过智谱 AI 开放平台(BigModel)的 Web Search API 提供网页搜索能力的命令行工具,并符合 Model-Code-Protocol (MCP) 规范。可以通过标准输入/输出(STDIO)与客户端通信
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"zhipu-web-search": {
"command": "npx",
"args": [
"cc-zhipu-web-search"
],
"env": {
"BIGMODEL_API_KEY": "<YOUR_BIGMODEL_API_KEY>"
}
}
}
}Tools
1使用智谱 Web Search API 进行网页检索
Overview
What is 智谱 Web Search MCP 工具(STDIO)?
A command-line tool that provides web search capabilities through the Zhipu AI Open Platform (BigModel) Web Search API, conforming to the Model Context Protocol (MCP) standard. It allows any MCP-compatible client, such as AI agents, to invoke web search functionality.
How to use 智谱 Web Search MCP 工具(STDIO)?
Integrate with an MCP client by adding a configuration entry in mcp.json. The server runs via npx (command cc-zhipu-web-search) and requires the environment variable BIGMODEL_API_KEY. The tool exposes a web-search function with parameters like query, search_engine, count, search_domain_filter, search_recency_filter, and content_size.
Key features of 智谱 Web Search MCP 工具(STDIO)?
- Calls Zhipu Web Search API with parameter conversion
- Formats JSON results into human-readable text
- Serves as an MCP server over STDIO
- Supports multiple search engines and result counts
- Allows domain filtering and time range filtering
- Controls web page summary length
Use cases of 智谱 Web Search MCP 工具(STDIO)?
- AI agents needing real-time web search results
- Limiting search to a specific domain (e.g.,
www.example.com) - Restricting results to recent time periods
- Controlling the number of returned results (1–50)
- Integrating web search into MCP-compatible chatbots or tools
FAQ from 智谱 Web Search MCP 工具(STDIO)?
What dependencies are needed?
A Zhipu AI API key from the BigModel Open Platform is required.
How is the server configured for MCP clients?
Add a zhipu-web-search entry in the client's mcp.json, using command: "npx", args: ["cc-zhipu-web-search"], and the BIGMODEL_API_KEY environment variable.
Is domain filtering supported?
Yes, the search_domain_filter parameter limits results to a specified domain (e.g., www.example.com).
What is the maximum query length?
The query parameter is limited to 70 characters.
What transport does this server use?
It uses STDIO (standard input/output) to communicate with the MCP client.
Frequently asked questions
What dependencies are needed?
A Zhipu AI API key from the BigModel Open Platform is required.
How is the server configured for MCP clients?
Add a `zhipu-web-search` entry in the client's `mcp.json`, using `command: "npx"`, `args: ["cc-zhipu-web-search"]`, and the `BIGMODEL_API_KEY` environment variable.
Is domain filtering supported?
Yes, the `search_domain_filter` parameter limits results to a specified domain (e.g., `www.example.com`).
What is the maximum query length?
The `query` parameter is limited to 70 characters.
What transport does this server use?
It uses STDIO (standard input/output) to communicate with the MCP client.
Basic information
More Search MCP servers
Goalie Trademark Search MCP
goalie-mcpSearch & filter 14M+ USPTO trademark records from an AI agent. This is a trademark MCP server, not a TSDR lookup.
Search Console Mcp
saurabhsharma2uSearch & analytics data as infrastructure — MCP server for Google Search Console, Bing Webmaster Tools, and GA4, designed for AI agents and automation.
🚀 OneSearch MCP Server: Web Search & Crawl & Scraper & Extract
yokingma🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
patent-literature-search-mcp
patsnapA professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.

Webz.io News Search
Webz.ioSearch global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Comments