Delivers weekly grocery plans, digests, and notifications through Telegram.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Gurkerl Recommender MCP recommend healthy groceries under €30 and explain the scoring"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Explainable grocery recommendations, with MCP integration.
Nutrition- and budget-aware grocery ranking, offer monitoring and weekly digests, with offline samples and optional MCP/Telegram integrations.
Technology: Python · SQLite · MCP · Optional Node.js bridge · Telegram
Explainable scoring for nutrition, price, promotions and close-to-expiry offers.
A dependency-free sample recommender and configurable monitoring pipeline.
Weekly plans/digests, notification deduplication and SQLite state.
An optional local MCP server and clients for authenticated external MCP services.
Related MCP server: Willys MCP Server
A personal recommendation toolkit with reproducible offline examples. External service ingestion and account tools require separate credentials and authorization. Recommendations do not provide medical nutrition advice or automatically place orders.
Requires Python 3.11+ for the documented setup; Node.js 22+ is needed only for the optional JavaScript bridge.
git clone https://github.com/Fernise/gurkerl-recommender-mcp.git
cd gurkerl-recommender-mcp
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e .
python -m gurkerl_recommender.cli --sample
python -m gurkerl_recommender.monitor_cli --config config.example.jsonThe sample configuration is offline and prints to the console. To expose the local recommendation tools through MCP:
python -m pip install -e '.[mcp]'
python -m gurkerl_recommender.serverFor the optional Node SDK helper, run npm ci first. See configuration, scoring and MCP integration notes. Real account credentials belong only in an ignored local .env file.
python -m unittest discover -s tests -vThe suite uses sample products and mocked external responses. Authenticated grocery access, MCP account tools and Telegram delivery are not exercised during CI.
Path | Responsibility |
| Scoring, models, sources, MCP clients and CLI commands |
| Offline scoring, monitor, client and notifier regressions |
| Optional Node MCP discovery helpers |
| Safe source/notifier configuration examples |
| Fictional recommendation preferences |
| Example service/timer units |
Original project code is licensed under the MIT License.
Third-party libraries and assets retain their own licenses.
This server cannot be deployed
USDA FoodData Central nutrient lookup, FDA recall watch, EU FMCG labelling via remote MCP
Unlock the power of food transparency with our Open Food Facts MCP server. Easily look up any food
Remote MCP for Living Stack offer discovery and buyer-authorized checkout preparation.
Real-time data APIs for 50+ commerce, grocery, social and maps platforms over one OAuth MCP server
