unified_searchLABSCO SUMMARY
One query, three sources, and the quota tools to survive it.
The interesting tool is the usage stats call — free-tier Google quotas are small enough that a research session can exhaust them without warning, and being able to ask how much is left turns that from a mystery failure into a decision. The cache is the other half of the same answer.
What it is
A Python search server that fans one query out across three sources concurrently and returns them together, with each source also available on its own. Around the search sits production plumbing — encrypted API key storage, input validation, Redis-backed caching and rate limits, Prometheus metrics, retries with exponential backoff and circuit breakers on the external APIs.
What you get
unified_search— search across scholar, web and youtube at once, choosing thesourcesandnum_resultssearch_google_scholar— academic papers filtered byauthorand ayear_start/year_endrangesearch_google_web— web search withlanguageandsafe_searchsettingssearch_youtube— video search filtered byvideo_durationandupload_date, ordered by criteria such as view countget_author_info— an author's profile from Google Scholarclear_cache— drop cached results for one source or all of themget_api_usage_stats— current usage against your API quotas- Health and metrics exposed as resources at
health://statusandmetrics://stats
Requirements
Two Google API keys: GOOGLE_API_KEY with a GOOGLE_CUSTOM_SEARCH_ENGINE_ID for web search, and YOUTUBE_API_KEY for video search — the same Cloud project can serve both. Google Scholar has no official API and is rate-limited in practice. Python 3.11 or higher, with pip install -r requirements.txt from a clone; the documented client entry runs python unified_search_server.py over stdio, and --transport streamable-http serves it over HTTP for a shared deployment. Redis is optional and only needed for distributed caching and rate limiting, set through MCP_REDIS_URL; MCP_ENCRYPTION_KEY and MCP_RATE_LIMIT_SECRET cover the security layer. Watch the free-tier limits: Google web search allows 100 queries per day and the YouTube API 10,000 units per day, roughly 100 searches.
Setup effort
Build from source — git clone https://github.com/JDeun/unified-search-mcp-server.git
USE CASES
01
Researching a topic from several angles at once
Fan one query across papers, the web and video, and read the three result sets together.
02
Finding papers by a specific author and period
Search Scholar filtered by author and year range, then pull the author's profile.
03
Staying inside a daily quota
Check remaining API usage before a long session and clear stale cache entries when results look out of date.
04
Finding a tutorial of the right length
Search video filtered by duration and upload date, ordered by view count.
7 tools
Listed in project docs. Your client may show a different list.
search_google_scholarsearch_google_websearch_youtubeget_author_infoclear_cacheget_api_usage_statsBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
- Python 3.11+
- GOOGLE_API_KEY in your environment
- YOUTUBE_API_KEY in your environment
- GOOGLE_CUSTOM_SEARCH_ENGINE_ID 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/JDeun/unified-search-mcp-server.git
cd unified-search-mcp-server
python -m venv venv
source venv/bin/activate
pip install -r requirements.txtMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"unified-search": {
"command": "python",
"args": [
"<YOUR_PATH_TO_UNIFIED_SEARCH_MCP_SERVER>/unified_search_server.py"
],
"env": {
"GOOGLE_API_KEY": "<YOUR_GOOGLE_API_KEY>",
"GOOGLE_CUSTOM_SEARCH_ENGINE_ID": "<YOUR_GOOGLE_CUSTOM_SEARCH_ENGINE_ID>",
"YOUTUBE_API_KEY": "<YOUR_YOUTUBE_API_KEY>"
}
}
}
}Use the virtual environment's Python as command — <YOUR_PATH_TO_UNIFIED_SEARCH_MCP_SERVER>/venv/bin/python (on Windows, venv\Scripts\python.exe) — so the client finds the packages installed above.
