Advertise
MCP.so
Sign In
P

Pepesto MCP Server

@pepesto-solutions

Repository

Basic information

Category

Other

Transports

stdio

Author

pepesto-solutions

Submitted by

Georgi Mitev

About Pepesto MCP Server

MCP server for the Pepesto's Grocery Shopping API - give your agent the ability to turn any recipe (a URL, plain text, or a photo) into a matched basket of real supermarket products with live prices, across 26 European supermarkets. The MCP covers the **recipe → matched cart** ha

#grocery-shopping#agentic-grocery-shopping#grocery-shopping-automation

Pepesto MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pepesto": {
      "command": "npx",
      "args": [
        "-y",
        "@pepesto/pepesto-mcp"
      ],
      "env": {
        "PEPESTO_API_KEY": "pep_sk_…"
      }
    }
  }
}

Pepesto MCP Server tools

6

`POST /oneshot`

`POST /parse`

`POST /suggest`

`POST /products`

`POST /catalog`

`POST /credits`

Overview

What is Pepesto MCP Server?

An MCP server for the Pepesto API that lets AI agents turn any recipe (URL, text, or photo) into a matched basket of real supermarket products with live prices across 26 European supermarkets.

How to use Pepesto MCP Server?

Add to Claude Desktop config or use claude mcp add with the environment variable PEPESTO_API_KEY. Run via npx -y @pepesto/pepesto-mcp. Obtain an API key by first purchasing credits at pepesto.com/pricing, then calling POST /link with your email.

Key features of Pepesto MCP Server

  • Turns any recipe into a matched supermarket cart
  • Supports 26 supermarkets across 10 European countries
  • Provides structured ingredient parsing from URLs, text, or images
  • Searches a 1M+ recipe graph for inspiration
  • Maps parsed ingredients to concrete products with live prices
  • Offers a full SKU dump tool for market analysis

Use cases of Pepesto MCP Server

  • One-shot recipe URL to a matched cart with a checkout link
  • Browse recipe suggestions, pick one, and match it at a chosen supermarket
  • Parse a specific recipe then map ingredients to products
  • Build a merged shopping list covering multiple recipes for a week
  • Compare matched cart totals across two supermarkets

Frequently asked questions

1

How do I get an API key?

Purchase a credit pack at pepesto.com/pricing, then call `POST /link` with your email. The key is returned only once—store it immediately.

2

Does this MCP place the actual order on the supermarket website?

No. It stops at a matched cart with prices. Finish the trip either via the Pepesto app (using the returned `redirect_url`) or by manually adding the SKUs on the supermarket’s own site.

3

Which supermarkets are supported?

26 supermarkets across the UK, Netherlands, Germany, Switzerland, Belgium, Ireland, Italy, Denmark, Norway, Poland, and Bulgaria. Full list in the README.

4

How is usage priced?

Pay-as-you-go credits that never expire. `pepesto_credits` is free; everyday calls are priced for routine agent use. `pepesto_catalog` is the heaviest call—cache its result for at least a day.

5

What tools are available?

Tools: `pepesto_oneshot`, `pepesto_parse`, `pepesto_suggest`, `pepesto_products`, `pepesto_catalog`, and `pepesto_credits`. Each wraps a specific API endpoint for the recipe-to-cart workflow.

Comments

More Other MCP servers

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Advertise