Web Search MCP Server

@matemiro

代码仓库

基本信息

分类

搜索

传输方式

stdio

作者

matemiro

关于 Web Search MCP Server

A Model Context Protocol (MCP) server that provides a web search tool using the Tavily API. This server enables AI models to search the internet and retrieve up-to-date information.

#mcp #mcp-server#tavily-search

Web Search MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP-Tavily-Web-Search-Server": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Web Search MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Web Search MCP Server?

Web Search MCP Server is a Model Context Protocol (MCP) server that provides a web search tool using the Tavily API. It acts as a bridge between AI models and the Tavily search engine, enabling models to search the internet and retrieve up-to-date information during conversations.

How to use Web Search MCP Server?

Install Python 3.13+ and uv, then clone the repository, set up a virtual environment, and install dependencies with uv pip sync. Create a .env file from the provided template and add your Tavily API key. Run the server with uv run web_search_server.py. The server uses the stdio transport method for MCP communication.

Key features of Web Search MCP Server

Real-time web search via Tavily API
Customizable search topic (general, news, finance)
Adjustable search depth (basic, advanced)
Maximum results and time range filtering (day, week, month, year)
Domain inclusion and exclusion lists

Use cases of Web Search MCP Server

AI assistants retrieving current internet information during conversations
Chatbots answering queries that require real-time data
Research agents gathering up-to-date results from specified domains
News or finance searches filtered by recent time ranges

常见问题

What exactly does this server do?

It exposes a single tool (`search_web_tool`) that lets AI models search the web via the Tavily API and return a list of results containing title, URL, content, and relevance score.

What are the runtime requirements?

Python 3.13+, the `uv` package installer/resolver, and a valid Tavily API key obtained from [tavily.com](https://tavily.com/).

How do I configure the Tavily API key?

Copy the `env-sample` file to `.env`, then edit `.env` to set `TAVILY_API_KEY=your-api-key-here`.

What parameters does the search tool accept?

It requires a `query` string and accepts optional parameters: `search_topic`, `search_depth`, `max_results`, `time_range`, `include_domains`, and `exclude_domains`.

How are errors handled?

If an error occurs during a search operation, the tool returns an error message describing the issue.

搜索分类下的更多 MCP 服务器

FlatHunt

Search and compare furnished apartments, studios and rooms in Berlin across multiple housing providers. FlatHunt supports filtering by budget, location, move-in date, rental duration, property type, size, amenities and r

Aguasto Research

Aguasto

Official read-only MCP access to Aguasto's public GPU, model and infrastructure research. Search published descriptions and retrieve canonical source links. Anonymous Streamable HTTP; GPU rental and token-based inference

VerifyAPI

Circuit Savers LLC

Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.

SaaS Think Tank — Software Research

SaaS Think Tank

Software research to help people choose the right tools. SaaS Think Tank publishes software comparisons, reviews and practical resources across categories, with dated findings, source links and clear limits. Current MCP

Google Search MCP Server

HasData

Hosted Google Search / SERP MCP server from HasData, no Google Cloud project. Organic results, AI Overview, People Also Ask, AI Mode, news and shopping for Claude, Cursor and any MCP client.