searchLABSCO SUMMARY
One tool, five knobs, nothing to learn.
The value of a search server is mostly in how little it costs the model to use, and a single call with named parameters is about as cheap as that gets — the difference between a quick check and a deep dive is one string. Retries and timeouts are handled inside rather than left to the client, which matters more than it sounds: a search that fails silently mid-answer is worse than one that takes another second.
What it is
A small Python MCP server in front of the Tavily search API. The whole surface is one tool with a handful of parameters, built so a model can reach for web results mid-reasoning without a separate research step.
What you get
- A
searchtool that takes aqueryand returns clean markdown-formatted results with snippet previews and source URLs search_depthset to basic or advanced, so a quick lookup and a deeper crawl are the same call with one parameter changedmax_resultsanywhere from 1 to 20, so the answer size is yours to cap- A
topicof news for stories rather than pages,include_imagesfor image results, andinclude_raw_contentwhen the snippet is not enough - Asynchronous request handling with automatic retries on failure and configurable timeouts, so a slow upstream does not hang the turn
Requirements
A Tavily API key, supplied as TAVILY_API_KEY — either in a .env file or in the env block of your client config. Python 3.11 or higher and the uv package manager. The package is mcp-tavily-search (version 0.2.0); install with uv pip install -e . from a clone and launch server.py with uv run.
Setup effort
Build from source — git clone https://github.com/arben-adm/tavily-mcp-search.git
USE CASES
01
Checking a fact mid-answer
Run a basic-depth search capped at a few results and read the snippets with their source URLs, without turning the reply into a research project.
02
Catching up on a developing story
Set the topic to news and raise the result count, so the response is recent coverage rather than evergreen pages.
03
Reading a source properly instead of skimming it
Ask for raw content alongside an advanced-depth search when the snippet is too thin to answer from.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. search_depth (basic or advanced), topic=news, max_results (1 to 20), include_images and include_raw_content are arguments of search, not separate tools.
Requires
- Python 3.11 or later
- 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
TERMINAL
git clone https://github.com/arben-adm/tavily-mcp-search.git
cd tavily-mcp-search
uv venv
uv pip install -e .MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"tavily-search": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_TAVILY_SEARCH_MCP>",
"run",
"server.py"
],
"env": {
"TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>"
}
}
}
}<YOUR_PATH_TO_MCP_TAVILY_SEARCH_MCP> is the full path of the mcp_tavily_search folder inside your clone. The clone is called tavily-mcp-search, so the path ends in tavily-mcp-search/mcp_tavily_search.
