searchLABSCO SUMMARY
One tool, two useful outputs: an answer and the sources it came from.
Getting the synthesised answer and the underlying URLs in the same response is what makes this usable for real questions — the model can answer straight away, and you can still click through when it matters. The depth setting is the only knob: basic for a quick lookup, advanced when the first pass was too shallow.
What it is
A small Python MCP server that runs searches through the Tavily API and returns the results as text — an AI-generated answer first, then the titles and URLs behind it.
What you get
- One tool,
search, taking a query and an optional search depth of basic or advanced - An AI answer synthesised from the results, so the assistant has something to work with immediately
- The source titles and URLs alongside it, so claims can be checked rather than taken on trust
- Server-side logging of each search and its outcome, written to a per-platform log directory
Requirements
A Tavily API key set as TAVILY_API_KEY, plus uv to run the cloned repository. On Windows also set PYTHONIOENCODING to utf-8. For Cursor, wrap the launch in a shell script that exports the key and starts the server. A Docker Compose setup is provided for Linux, where the desktop client is not available.
Setup effort
Build from source
USE CASES
01
Answering a question about something recent
Search and get a synthesised answer plus the sources, instead of the model guessing from training data.
02
Checking where a claim came from
Read the titles and URLs returned with the answer and open the ones that carry the weight.
03
Going deeper when the first pass was thin
Re-run the same query with the advanced depth rather than rephrasing and hoping.
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.
Requires
- uv
- TAVILY_API_KEY in your environment
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/Tomatio13/mcp-server-tavily.gitMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"tavily-search": {
"command": "uv",
"args": [
"--directory",
"C:\\<YOUR_PATH>\\mcp-server-tavily",
"run",
"tavily-search"
],
"env": {
"TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>",
"PYTHONIOENCODING": "utf-8"
}
}
}
}C:\<YOUR_PATH>\mcp-server-tavily is the full path of the folder git clone created (on macOS or Linux, a normal /-separated path).
Cursor
Create a shell script (e.g. script.sh) with this content; <YOUR_TARGET_DIR> is the full path of your clone:
CURSOR · TERMINAL
#!/bin/bash
TARGET_DIR=<YOUR_TARGET_DIR>
cd "${TARGET_DIR}"
export TAVILY_API_KEY="<YOUR_TAVILY_API_KEY>"
export PYTHONIOENCODING=utf-8
uv --directory $PWD run tavily-searchThen open Cursor's MCP Server settings, set Name: tavily-search, Type: command, Command: the full path to that script (/path/to/your/script.sh), and save.
