MCP.so
ログイン

MCP2Tavily

@mcp2everything

リポジトリ

MCP2Tavily について

一个MCP服务器，让你的Claude Cline以及Langchain实现网络搜索功能。An MCP server that allows your Claude Cline and Langchain to implement network search functions.

#mcp2tavily#web-search#mcp-server

基本情報

カテゴリ

AI とエージェント

ランタイム

python

トランスポート

stdio

公開者

mcp2everything

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp2tavily": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP2Tavily?

MCP2Tavily is an MCP protocol server that enables web search functionality through the Tavily API. It is designed for developers using AI assistants like Claude who need to perform web searches via the Model Context Protocol.

How to use MCP2Tavily?

Clone the repository, create a .env file with your Tavily API key, set up a virtual environment with UV, and install dependencies via uv sync. Then install as a Claude extension with fastmcp install mcp2tavily.py or test using MCP Inspector with fastmcp dev mcp2tavily.py. A manual JSON configuration is also provided for integration with Cline, Continue, and Claude.

Key features of MCP2Tavily

  • Provides two web search tools: search_web and search_web_info
  • search_web_info includes Chinese-language descriptions
  • Easy installation as a Claude extension via FastMCP
  • Supports development and testing with MCP Inspector
  • Uses Tavily API for high-quality web search results

Use cases of MCP2Tavily

  • Enabling Claude or other MCP-compatible assistants to search the web
  • Integrating real-time web search into AI workflows
  • Creating custom search tools for multi-agent systems
  • Building AI applications that require recent or specific online information

FAQ from MCP2Tavily

What are the prerequisites for MCP2Tavily?

Python 3.11 or higher, the UV package manager, and a valid Tavily API key are required.

How do I obtain a Tavily API key?

You must sign up for a Tavily account and generate an API key. The key is stored in the TAVILY_API_KEY environment variable.

Does MCP2Tavily store any data?

No. MCP2Tavily itself does not store data; search queries are sent to the Tavily API and results are returned directly.

What transport protocol does MCP2Tavily use?

The README does not specify a transport protocol, but it uses the MCP standard and is invoked via FastMCP, which typically uses stdio or HTTP.

Can I use MCP2Tavily with Cline or Continue?

Yes. The README provides a JSON configuration example for integrating MCP2Tavily with Cline, Continue, and Claude by specifying the uv command and required arguments.

コメント

「AI とエージェント」の他のコンテンツ

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K