MatMCP
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., "@MatMCP find organic milk and add 2 cartons to my basket"
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.
MatMCP 🛒
An MCP (Model Context Protocol) server that provides AI assistants with tools to interact with Mathem.se, a Swedish online grocery store. Search for ingredients, add items to your basket, and manage recipes directly through your AI assistant.
Features
Search Ingredients: Find products on Mathem.se by name or description
Add to Basket: Add products directly to your Mathem.se shopping cart
Recipe Management: List and fetch detailed recipe information
Structured Data: Get clean, structured product and recipe data
Related MCP server: Rohlik MCP Server
Prerequisites
macOS/Linux: This guide assumes macOS, but Linux instructions are similar
Python 3.12+: Required for the project
uv: Fast Python package manager
Mathem.se Account: For adding items to basket functionality
Installation
1. Install uv (Python package manager)
brew install uv2. Clone and setup the project
git clone <your-repo-url>
cd matmcp3. Install dependencies
uv sync4. Configure Mathem.se authentication (optional)
For basket functionality, you need to provide your Mathem.se session cookies:
Copy the example cookie file:
cp cookie.txt.example cookie.txtGet your session cookies from Mathem.se:
Open your browser and go to mathem.se
Log in to your account
Open Developer Tools (F12)
Go to the Network tab
Refresh the page
Find a request to mathem.se and copy the Cookie header value
Paste it into
cookie.txt
The format should look like:
sessionid=your_session_id_here; csrftoken=your_csrf_token_here; other_cookies=value
Note: Without cookies, you can still search for ingredients, but adding to basket will not work.
Claude Desktop Integration
Add this MCP server to your Claude Desktop configuration:
1. Open Claude Desktop config
# macOS
open ~/Library/Application\ Support/Claude/claude_desktop_config.json
# Linux
open ~/.config/claude/claude_desktop_config.json2. Add the server configuration
Replace /YOUR/PATH/TO/matmcp with your actual project directory:
{
"mcpServers": {
"mathem": {
"command": "uv",
"args": [
"--directory",
"/YOUR/PATH/TO/matmcp",
"run",
"mathem.py"
]
}
}
}3. Restart Claude Desktop
Close and reopen Claude Desktop to load the new MCP server.
Usage
Once configured, you can ask Claude to:
Search for ingredients: "Find organic tomatoes on Mathem"
Add items to basket: "Add 2 packages of pasta to my Mathem basket"
Get recipes: "Show me the available recipes"
Recipe details: "Get the details for recipe number 1"
Available Tools
search_mathem_ingredients(query: str)
Search for products on Mathem.se
Example: Search for "organic milk"
add_to_mathem_basket(product_id: int, quantity: int = 1)
Add a product to your Mathem.se shopping basket
Requirements: Valid session cookies in cookie.txt
list_recipes()
List all available recipes from recipes.csv
get_recipe_by_index(index: int)
Get detailed recipe information by index
Development
Running tests
uv run pytestRunning the server directly
uv run mathem.pyAdding recipes
Edit recipes.csv to add new recipes with columns: id, title, url
License
This project is for educational and personal use. Please respect Mathem.se's terms of service when using this tool.
Available Tools
4 toolsadd_to_mathem_basketC
Add a product to the Mathem.se shopping basket
Inputs: product_id (required), quantity. Returns: result
get_recipe_by_indexC
Get a recipe by index from the list
Inputs: index (required). Returns: object
list_recipesB
List available recipes
Inputs: no named parameters. Returns: result
search_mathem_ingredientsB
Search for ingredients on Mathem.se grocery store
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The tools have mostly distinct purposes: list_recipes and get_recipe_by_index handle recipe browsing, while add_to_mathem_basket and search_mathem_ingredients focus on shopping basket and ingredient search. However, there is a slight overlap in the recipe domain where list_recipes and get_recipe_by_index could be confused if an agent needs to retrieve a specific recipe, but the descriptions clarify their distinct roles.
The naming is mixed with some consistency: list_recipes and get_recipe_by_index follow a verb_noun pattern, but add_to_mathem_basket uses a prepositional phrase and search_mathem_ingredients includes the domain name. This creates a readable but inconsistent convention across the tool set, with deviations from a uniform pattern.
With 4 tools, the count is reasonable for a server focused on recipes and grocery shopping. It covers key operations like listing, retrieving, searching, and adding items, making it well-scoped for its apparent purpose, though it could potentially benefit from additional tools for a more complete workflow.
The tool set covers basic recipe browsing and ingredient shopping, but there are notable gaps. For example, there is no tool to manage the shopping basket beyond adding items (e.g., remove or view items), and no update or delete operations for recipes. This limits the agent's ability to handle full lifecycle tasks in the domain.
Maintenance
Related MCP Connectors
Recipe search, ingredient matching, nutrition filters and a private cookbook for any AI agent.
Search structured recipes, scale servings, match pantry ingredients, and build shopping lists.
Turn any shopping list into a ready-to-checkout grocery cart across 26 European supermarkets.
AI-powered kitchen management — pantry, recipes, meal plans, shopping lists
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables agentic grocery shopping on Oda (Norway) and Mathem (Sweden) platforms through an MCP-compatible interface. Users can search for products, manage their shopping cart, and access order history using natural language commands.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to search grocery products, manage shopping carts, retrieve account, order, delivery, and premium information, and get personalized meal suggestions and discounted items across multiple European grocery delivery platforms.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to search grocery products, manage shopping carts, access account and order information, and get personalized shopping suggestions across multiple Rohlik Group grocery platforms.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to search grocery products, manage shopping carts, and access account and order information across multiple online grocery platforms. It also supports smart shopping suggestions, deals, delivery slots, and order history.MIT