tavily-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tavily-mcpwhat are the latest advancements in AI?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tavily-mcp
A web search and extraction MCP server powered by Tavily, built on Dedalus.
Tools
Tool | Description |
| Search the web with AI-generated answer synthesis |
| Extract clean content from URLs |
| Ask a question and get a direct answer with sources |
Environment Variables
Variable | Required | Description |
| Yes | Tavily API key ( |
| Yes | Dedalus platform API key |
| No | Dedalus API base URL |
| No | Dedalus auth server URL (default: |
Quick Start
# Install dependencies
uv sync
# Set environment variables
cp .env.example .env
# Edit .env with your keys
# Run the server
uv run python src/main.pyTesting
# Unit tests (no API key needed)
uv run pytest tests/test_tools.py
# Live connection tests (requires TAVILY_API_KEY)
uv run pytest tests/test_connection_live.pySource Decision
Decision: Build native (Python)
The official tavily-ai/tavily-mcp is implemented in TypeScript using @modelcontextprotocol/sdk. Since our infrastructure requires Python with Dedalus DAuth integration, we build natively using dedalus-mcp. The official implementation served as a functional specification for tool definitions and API endpoints.
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
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/chenzhaoxuan0/tavily-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server