Pepesto Agent-to-Cart
Server Details
Turn any shopping list into a ready-to-checkout grocery cart across 26 European supermarkets.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility for confusion or overlap between tools.
With a single tool, naming consistency is trivially maintained. The name uses a clear verb_noun structure.
A single tool for the specific purpose of creating a cart link is functional, but it feels thin for a server scope. Typically 3-15 tools are expected for good coherence.
The server's purpose is to convert a shopping list into a cart link, and the single tool fully covers this operation with no obvious missing functionality.
Available Tools
1 toolpepesto_create_cartPepesto Agent-to-CartAInspect
Turn a free-form shopping list into a ready-to-open Pepesto cart link.
This tool is FREE and needs NO API key or authentication. Nothing is matched or charged when you call it: matching products and pricing happen LAZILY only after the USER opens the returned link in the Pepesto app, and the USER pays at checkout in the app — never here, never you.
Covers 26 European supermarkets. The response is a single block of Markdown that already contains a labeled, tappable link. Clients should surface that Markdown link AS-IS (render the link) and must NOT show the raw URL or rewrite the caption.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | Optional locale/region hint, e.g. 'en-CH' or 'de-DE'. | |
| shopping_list | Yes | Free-form shopping list. One item per line or comma-separated, e.g. '2 bananas\nmilk\n500g spaghetti'. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description thoroughly discloses behavior: no matching or charging at call time, lazy processing only after user opens link, free usage, no auth required. Also describes response format (Markdown with labeled link). Fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise yet comprehensive. First sentence states purpose, followed by bullet points with key usage notes. No redundant sentences, every line adds value. Well-structured for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description covers all essential aspects: input format, output format, behavioral safety (no charges, no auth), and geographic scope. Complete for an AI agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds value by giving examples for shopping_list (e.g., '2 bananas\nmilk') and locale (e.g., 'en-CH'), which clarifies usage beyond the schema definitions. Not a 5 because schema already covers basics well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: turning a free-form shopping list into a Pepesto cart link. It specifies input, output, and context (European supermarkets, no auth). Distinguishes itself from potential alternatives by emphasizing the lazy matching and pricing, making purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use (free-form shopping list), what not to worry about (no API key, no immediate charges), and how to handle the response (surface Markdown link as-is, avoid showing raw URL or rewriting caption). Provides clear context for usage without references to siblings, but self-contained.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
pepesto_create_cart
Related MCP Connectors
Live prices, deals & optimal multi-stop shopping routes for German grocery & drug stores.
AI meal plans that fill your Kroger/Instacart cart - pantry-aware lists, all from chat.
AI-powered kitchen management — pantry, recipes, meal plans, shopping lists
Persistent shopping memory for AI assistants. The AI reasons; Kaufliste stores and executes.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables cross-store price comparison and recipe-driven cart automation for Israeli grocery stores Shufersal and Tiv Taam, with an extensible architecture for additional stores.14-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Rohlik Group's online grocery delivery services across multiple European countries, supporting product search, shopping cart management, order history analysis, and personalized meal suggestions based on purchase patterns.15 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables personalized Mercadona grocery orders via natural language, with Nutri-Score prioritization and supervised cart execution (no payment). Supports user intake, product search, and integration with external menu systems.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with Picnic online supermarket for grocery shopping, meal planning, cart management, delivery tracking, and budget-conscious shopping in Netherlands and Germany.103 npm101MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.