deep_searchLABSCO SUMMARY
An agent can run a proper sweep instead of a single search.
Deep search issues several rounds of queries, reads across them and returns one grounded answer; quick search stays there for the questions that only need a look. The depth is a parameter, so the cost of a run is something you decide.
What it is
A research agent behind three calls, built on LangGraph and Gemini. Deep search runs multiple search iterations and folds the results together; quick search is a single pass. Citations come from Gemini's grounding metadata rather than being assembled afterwards.
What you get
- A multi-round investigation of a topic, with the iteration count and results per query under your control
- A single-pass search for questions that do not need rounds
- Search language selectable per call
- Source citations attached automatically, from grounding metadata
- The state of the configured search tools, readable before you depend on them
Requirements
Python 3.10 or newer, uv, and a Gemini API key in the environment. Runs via uvx from the cloned project. The documentation is in Japanese.
Setup effort
One command plus a key — uvx --from . langgraph-deep-search, then supply credentials
USE CASES
01
Comparing options before you pick one
Ask for the comparison outright and let it run several rounds of searches, so the answer rests on more than the first page of results.
02
Settling a question one search would answer
Use the single-pass call and keep the round trips down when the question does not warrant an investigation.
03
Keeping a research run inside a budget
Cap the iterations and results per query on the call itself, so depth is a decision rather than whatever the agent felt like.
04
Checking the server is wired to search before relying on it
Read the search tool status back, so a run that returns nothing is diagnosed rather than retried.
3 tools
Listed in project docs. Your client may show a different list.
quick_searchget_search_toolsBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- Python 3.10 or later
- GEMINI_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx --from . langgraph-deep-searchMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"langgraph-deep-search": {
"command": "uvx",
"args": [
"--from",
"<YOUR_PATH_TO_DEEP_SEARCH_MCP_SERVER>",
"langgraph-deep-search"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}
