MCP cover image
See in Github
2025-03-30

模型控制协议(MCP)服务器的Rust实现,该服务器集成了Tavily强大的搜索和Web内容提取功能。该服务器使AI代理和LLM系统能够通过标准化的JSON-RPC接口从URL进行实时Web搜索,并从URL中提取内容,从而使其非常适合构建AI工具。

1

Github Watches

0

Github Forks

0

Github Stars

Tavily-Anet-MCP Server

A Rust implementation of the Model Control Protocol (MCP) server that provides Tavily search and content extraction capabilities via a standardized protocol.

This server integrates the powerful Tavily API with the Anet MCP framework, enabling AI agents to perform web searches and extract content from URLs. It is designed for developers building AI agent systems, LLM-based tools, or research automation that requires up-to-date web information.


Features

  • ✅ Tavily Search integration with comprehensive parameters
  • 📄 Tavily Extract for content retrieval from URLs
  • 🔄 NATS transport layer for message passing
  • 🛠️ JSON-RPC 2.0 compatible API
  • ⚡ Asynchronous request handling with Tokio
  • 🔍 Advanced search capabilities including domain filtering, time ranges, and topic selection

Requirements

  • Rust 1.70+
  • NATS server running locally or accessible via network
  • Tavily API Key (get one from Tavily's website)

Installation

Clone the repository and build the server:

git clone https://github.com/yourusername/tavily-anet-mcp.git
cd tavily-anet-mcp

Add your Tavily API key to a .env file:

TAVILY_API_KEY=your_api_key_here
NATS_URL=nats://localhost:4222
MCP_SUBJECT=mcp.requests

Getting Started

Running the Server

# Start a NATS server in another terminal or ensure one is already running
# Example:
nats-server

# Run the Tavily MCP server
cargo run

Testing the Server

You can test the server using the included test client:

cargo run --example test_client

This will send various requests to the server (initialize, listTools, search, extract) and print the responses.


Available Tools

1. Tavily Search

A powerful web search tool that provides comprehensive, real-time results using Tavily's AI search engine.

Parameters:

  • query (required): Search query string
  • search_depth: "basic" or "advanced" (default: "basic")
  • topic: "general" or "news" (default: "general")
  • days: Number of days back for results (for news topic)
  • time_range: "day", "week", "month", "year"
  • max_results: 5-20 (default: 10)
  • include_images: Boolean
  • include_raw_content: Boolean
  • include_domains: Array of domains to include
  • exclude_domains: Array of domains to exclude

Example:

{
  "name": "tavily-search",
  "arguments": {
    "query": "Latest developments in AI",
    "max_results": 5,
    "topic": "news",
    "days": 7
  }
}

2. Tavily Extract

A tool for extracting raw content from web pages.

Parameters:

  • urls (required): Array of URLs to extract content from
  • extract_depth: "basic" or "advanced" (default: "basic")
  • include_images: Boolean (default: false)

Example:

{
  "name": "tavily-extract",
  "arguments": {
    "urls": ["https://www.rust-lang.org/"],
    "extract_depth": "advanced",
    "include_images": true
  }
}

Architecture

The server follows a modular design:

  • tools – Tavily Search and Extract implementations
  • models – Tavily API response structures
  • utils – Formatting and helper functions
  • transport – NATS message transport layer

Development

Adding New Features

To extend the server with additional Tavily capabilities:

  1. Define response structures in src/models/tavily.rs
  2. Implement the tool in src/tools/ following the Tool trait
  3. Add formatting functions in src/utils/formatter.rs
  4. Register the tool in src/main.rs

Troubleshooting

  • Ensure your Tavily API key is valid and correctly set in the environment variables
  • Check that the NATS server is running and accessible
  • Verify the request format matches the expected input schema for each tool

License

MIT License


Acknowledgements

This project is built on top of the Anet MCP Server framework and integrates with the Tavily API.

相关推荐

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • Lists Tailwind CSS classes in monospaced font

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • modelcontextprotocol
  • 模型上下文协议服务器

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

  • ravitemer
  • 一个功能强大的Neovim插件,用于管理MCP(模型上下文协议)服务器

    Reviews

    3 (1)
    Avatar
    user_0wBAQB63
    2025-04-16

    As a dedicated user of Tavily-anet-mcp by marekkucak, I am thoroughly impressed by its functionalities and seamless performance. This tool stands out for its user-friendly interface and effective features, which greatly enhance my daily tasks. I highly recommend checking it out at https://github.com/marekkucak/tavily-anet-mcp.