tavily-searchLABSCO SUMMARY
The Tavily toolset, with SSE as a first-class option.
Search and extract are the pair most people want, and having map and crawl next to them means "read this whole site" is one server rather than three. The reason to pick this implementation is deployment: it runs as a shared SSE service in a container, so several clients use one process and one API key instead of each spawning their own.
What it is
A FastMCP implementation of the Tavily tools that runs either as a local stdio process or as a standalone SSE service, including a Docker image. Same tools either way; the difference is whether one client launches it or several connect to it.
What you get
tavily-searchfor real-time web searchtavily-extractfor pulling content out of a specific page- A mapping tool that builds a structured map of a website
- A crawler that walks a site systematically
- Two entry points from one install:
tavily-mcp-sseandtavily-mcp-stdio - A Dockerfile, so the SSE server can run as a container on port 8000
Requirements
A Tavily account and API key in TAVILY_API_KEY, plus git and uv; Docker only if you want the containerised SSE server. Copy .env.example to .env and put the key there, then uv run --env-file .env tavily-mcp-sse. TAVILY_MCP_PORT changes the SSE port. Version 0.1.0.
Setup effort
Build from source — git clone https://github.com/tsmndev/tavily-mcp-sse.git
USE CASES
01
Answering a question that needs the current web
Run a real-time search and read what comes back rather than relying on training data.
02
Getting the actual content of a page
Extract the text from a specific URL instead of working off a search snippet.
03
Sharing one search backend across clients
Run the SSE server in a container and point every client at it, with the key in one place.
2 tools
Listed in project docs. Your client may show a different list.
tavily-extractBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation. Map and crawl tools are also described, but their names are not documented.
Requires
TAVILY_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
Install uv (Linux and macOS)
TERMINAL
curl -LsSf https://astral.sh/uv/install.sh | shClone the repository and copy the example env file, then put your TAVILY_API_KEY in .env
TERMINAL
git clone https://github.com/tsmndev/tavily-mcp-sse.git
cd tavily-mcp-sse
cp .env.example .envMCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"tavily-mcp-server": {
"command": "uv",
"args": [
"run",
"--directory",
"<YOUR_LOCATION_TO_REPO>",
"tavily-mcp-stdio"
],
"env": {
"TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>"
}
}
}
}
