Skip to main content
Glama
enesjakozh

Tavily Search MCP Agent

by arben-adm
GitHub
Python
MIT License
1
  • Apple
  • Linux
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

🔍 My Tavily Search MCP Agent

I've created a powerful Model Context Protocol (MCP) Server powered by the Tavily API. With this, you can get high-quality, reliable information from business, news, finance, and politics - all through a robust and developer-friendly interface.

smithery badge Tavily Search Agent MCP Server CI codecov

🌟 Why I Built Tavily Search MCP

In today's fast-paced digital landscape, I recognized the need for quick access to precise information. I needed a web search tool that works with my sequential thinking MCP server. That's why I developed Tavily Search MCP, which excels with:

⚡️ Lightning-fast async search responses
🛡️ Built-in fault tolerance with automatic retries
🎯 Clean, markdown-formatted results
🔍 Smart content snippets
🛠️ Comprehensive error handling
🖼️ Optional image results
📰 Specialized news search

🚀 Quick Start

Installing via Smithery

To install Tavily Search for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-tavily-search --client claude

Installing Manually

Here's how you can get up and running with my project in minutes:

# 1. Create environment uv venv && .venv\Scripts\activate # Windows # OR uv venv && source .venv/bin/activate # Unix/MacOS # 2. Install dependencies uv pip install -e . # 3. Set up configuration echo TAVILY_API_KEY=your-key-here > .env # 4. Start server cd mcp_tavily_search && uv run server.py

💡 Core Features

⚡️ Performance & Reliability

  • I've implemented asynchronous request handling

  • Built-in error handling and automatic retries

  • Configurable request timeouts

  • Comprehensive logging system

🎯 Search Configuration

  • I've made the search depth configurable (basic/advanced)

  • Adjustable result limits (1-20 results)

  • Clean markdown-formatted output

  • Snippet previews with source URLs

  • Optional image results

  • Specialized news search topic

🛡️ Error Handling

  • API authentication validation

  • Rate limit detection

  • Network error recovery

  • Request timeout management

🛠️ Developer Integration

Prerequisites

Claude Desktop Setup

I've optimized the Claude Desktop experience with this configuration:

{ "mcpServers": { "tavily-search": { "command": "uv", "args": [ "--directory", "/path/to/mcp-tavily-search/mcp_tavily_search", "run", "server.py" ], "env": { "TAVILY_API_KEY": "YOUR-API-KEY" } } } }

📁 Configuration paths:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Unix/MacOS: ~/.config/Claude/claude_desktop_config.json

Project Architecture

I've designed a clean, modular structure to make development a breeze:

mcp-tavily-search/ ├── mcp_tavily_search/ # Core package │ ├── server.py # Server implementation │ ├── client.py # Tavily API client │ ├── test_server.py # Server tests │ ├── test_client.py # Client tests │ └── __init__.py # Package initialization ├── .env # Environment configuration ├── README.md # Documentation └── pyproject.toml # Project configuration

Key Components

Server (server.py)

  • I've implemented the MCP protocol

  • Request handling and routing

  • Error recovery and health monitoring

Client (client.py)

  • Tavily API integration

  • Retry mechanism with exponential backoff

  • Result formatting and processing

  • Error handling and logging

Tests (test_server.py and test_client.py)

  • Comprehensive unit tests for both server and client

  • Ensures reliability and correctness of the implementation

Usage Examples

Here are some examples of how to use the enhanced search capabilities I've implemented:

  1. Basic search:

{ "name": "search", "arguments": { "query": "Latest news on artificial intelligence" } }

  1. Advanced search with images:

{ "name": "search", "arguments": { "query": "Elon Musk SpaceX achievements", "search_depth": "advanced", "include_images": true, "max_results": 10 } }

  1. News-specific search:

{ "name": "search", "arguments": { "query": "Climate change impact on agriculture", "topic": "news", "max_results": 5 } }

  1. Search with raw content:

{ "name": "search", "arguments": { "query": "Python programming best practices", "include_raw_content": true, "max_results": 3 } }

Troubleshooting Guide

Connection Issues

If things don't work as expected, follow these steps I've outlined:

  1. Verify your configuration paths

  2. Check the Claude Desktop logs:

    # Windows type %APPDATA%\Claude\logs\latest.log # Unix/MacOS cat ~/.config/Claude/logs/latest.log

  3. Test the server manually using the quick start commands

API Troubleshooting

If you're experiencing API issues:

  1. Validate your API key permissions

  2. Check your network connection

  3. Monitor the API response in the server logs

Running Tests

To run the unit tests for this project, follow these steps:

  1. Install the development dependencies:

    uv pip install -e ".[dev]"

  2. Run the tests using pytest:

    pytest mcp_tavily_search

This will run all the tests in the mcp_tavily_search directory, including both test_client.py and test_server.py.

Community and Support

  • I encourage you to report issues and contribute on GitHub

  • Share your implementations and improvements

  • Join our discussions and help others

Security and Best Practices

Security is paramount in my implementation. The server includes:

  • Secure API key handling through environment variables

  • Automatic request timeout management

  • Comprehensive error tracking and logging

License

I've licensed this project under MIT. See the LICENSE file for details.

Acknowledgments

I'd like to give special thanks to:

  • The innovative Tavily API team

  • The MCP protocol community

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

This MCP server performs multi-topic searches in business, news, finance, and politics using the Tavily API, providing high-quality sources and intelligent summaries.

  1. 🌟 Why I Built Tavily Search MCP
    1. 🚀 Quick Start
      1. Installing via Smithery
      2. Installing Manually
    2. 💡 Core Features
      1. ⚡️ Performance & Reliability
      2. 🎯 Search Configuration
      3. 🛡️ Error Handling
    3. 🛠️ Developer Integration
      1. Prerequisites
      2. Claude Desktop Setup
    4. Project Architecture
      1. Key Components
        1. Server (server.py)
        2. Client (client.py)
        3. Tests (test_server.py and test_client.py)
      2. Usage Examples
        1. Troubleshooting Guide
          1. Connection Issues
          2. API Troubleshooting
        2. Running Tests
          1. Community and Support
            1. Security and Best Practices
              1. License
                1. Acknowledgments

                  Related Resources

                  Related MCP Servers

                  • tavily-search-mcp-server

                    apappascs
                    A
                    security
                    A
                    license
                    A
                    quality
                    An MCP server implementation that integrates the Tavily Search API, providing optimized search capabilities for LLMs.
                    Last updated -
                    2
                    MIT License
                    • Apple

                  • MCP2Tavily

                    mcp2everything
                    A
                    security
                    F
                    license
                    A
                    quality
                    An MCP protocol server that enables web search functionality using the Tavily API, allowing AI assistants to perform internet searches in real-time.
                    Last updated -
                    4
                    4

                  • metasearch-mcp

                    YeonwooSung
                    -
                    security
                    A
                    license
                    -
                    quality
                    MCP server for using various search tools like Tavily API. Planning to support various search tools (i.e. wiki search, searxng, etc)
                    Last updated -
                    3
                    MIT License
                    • Apple
                    • Linux

                  • Tavily News Search MCP Server

                    binhtrongg
                    -
                    security
                    F
                    license
                    -
                    quality
                    A remote MCP server that enables searching for news articles on specific topics through the Tavily API without requiring authentication.
                    Last updated -

                  View all related MCP servers

                  Appeared in Searches

                  New MCP Servers

                  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/arben-adm/tavily-mcp-search'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server