Which integrations are available for this server?

Integrates with Klarna's Agentic Product Protocol to provide structured product discovery, search, comparison, feed conversion, schema generation, and availability checking for AI shopping agents.

How do I use Agentic Product Protocol MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agentic Product Protocol MCP Server search for organic chocolate bars" 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.

Agentic Product Protocol MCP Server

by AiAgentKarl

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Agentic Product Protocol MCP Server

Klarna-style product discovery for AI shopping agents.

Makes product catalogs machine-readable so AI agents can search, compare, and purchase products programmatically — no screen scraping, no landing pages.

The Problem

Today's e-commerce is built for humans: landing pages, image carousels, "Add to Cart" buttons. AI shopping agents can't efficiently navigate this. They need structured product data — not HTML.

Klarna introduced the Agentic Product Protocol (December 2025) to solve exactly this: a standardized way for merchants to expose their product catalogs to AI agents. Think of it as RSS feeds, but for shopping.

Related MCP server: Nexbid

What This Server Does

This MCP server implements the core ideas of agentic product discovery:

Structured search results — not web pages, but clean JSON with name, price, nutrition, ratings
Product comparison — side-by-side structured comparison across multiple dimensions
Feed conversion — take any product feed (JSON, CSV, Open Food Facts) and normalize it into an agent-friendly schema
Schema generation — convert raw product data into the Agentic Product Protocol format
Availability checking — real-time product status in a machine-readable format

Uses Open Food Facts as a demo data source — works with any product feed.

Installation

pip install agentic-product-protocol-mcp

Or with uvx (no install needed):

uvx agentic-product-protocol-mcp

Configuration

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "product-protocol": {
      "command": "uvx",
      "args": ["agentic-product-protocol-mcp"]
    }
  }
}

Claude Code (CLI)

claude mcp add product-protocol -- uvx agentic-product-protocol-mcp

Tools

Tool	Description
`search_products`	Search products with structured results (name, nutrition, labels, stores)
`get_product_details`	Get full product data by barcode/ID
`compare_products`	Side-by-side comparison of 2-5 products
`convert_feed`	Convert JSON/CSV/OFF feeds into normalized agent schema
`generate_product_schema`	Generate Agentic Product Protocol schema from raw data
`check_availability`	Check product availability and store information

Example Usage

Search for products:

"Search for organic chocolate bars"

Compare products:

"Compare these three chocolate bars: 3017620422003, 7622210449283, 7613034626844"

Convert a feed:

"Convert this Open Food Facts search into agent-friendly format: https://world.openfoodfacts.org/cgi/search.pl?search_terms=protein+bar&page_size=10"

Generate schema:

"Generate an agentic product schema for this product data: {name: 'Widget Pro', price: 29.99, category: 'Electronics'}"

Why Structured Feeds > Landing Pages

	Landing Pages	Structured Feeds
Parsing	Screen scraping, fragile	Clean JSON, reliable
Speed	Load page → parse DOM → extract	Single API call
Accuracy	Layout changes break everything	Schema-validated
Comparison	Manual extraction per site	Normalized across sources
Agent UX	Built for human eyes	Built for agent consumption

Data Source

This server uses Open Food Facts as its demo data source — a free, open, community-built database of food products from around the world. No API key required.

For production use, connect your own product feeds using the convert_feed tool with JSON or CSV format.

More MCP Servers by AiAgentKarl

Category	Servers
🔗 Blockchain	Solana
🌍 Data	Weather · Germany · Agriculture · Space · Aviation · EU Companies
🔒 Security	Cybersecurity · Policy Gateway · Audit Trail
🤖 Agent Infra	Memory · Directory · Hub · Reputation
🔬 Research	Academic · LLM Benchmark · Legal

→ Full catalog (40+ servers)

License

MIT

Available Tools

6 tools

check_availabilityA

Check real-time product availability and pricing.

Fetches current product data and returns availability status, store information, and last-updated timestamp.

Note: Open Food Facts is a community database — availability reflects reported store data, not real-time inventory.

Args: product_id: Product barcode/EAN to check

Inputs: product_id (required). Returns: object

compare_productsA

Side-by-side product comparison for AI agents.

Compares multiple products across key dimensions: nutrition, labels, environmental impact, and ingredients.

Args: product_ids: List of product barcodes to compare (2-5 products)

Inputs: product_ids (required). Returns: object

convert_feedA

Convert a product feed URL into agent-friendly normalized schema.

Takes any product feed (JSON, CSV, Open Food Facts) and converts it into a standardized format that AI agents can easily consume.

Args: feed_url: URL to the product feed (JSON or CSV) format: Feed format — "openfoodfacts" (OFF search URL), "json" (generic JSON), or "csv" (CSV file)

Inputs: feed_url (required), format. Returns: object

generate_product_schemaA

Generate a standardized agent-readable product listing.

Takes raw product data and generates a structured schema following the Agentic Product Protocol concept — making products machine-readable for AI shopping agents.

The output schema includes:

Unique identification
Structured attributes (name, brand, category)
Pricing with currency
Availability status
Specifications and nutrition
Agent action hints (comparable, purchasable)

Args: product_data: Raw product data dict with fields like name, price, description, category, etc.

Inputs: product_data (required). Returns: object

get_product_detailsA

Get full structured product data by ID (barcode).

Returns complete product information including nutrition facts, ingredients, allergens, certifications, and environmental scores.

Args: product_id: Product barcode/EAN (e.g. "3017620422003" for Nutella)

Inputs: product_id (required). Returns: object

search_productsA

Search products with agent-friendly structured results.

Returns normalized product data including name, categories, nutrition scores, labels, and availability information. Uses Open Food Facts as demo data source.

Args: query: Search term (e.g. "organic chocolate", "vegan protein") category: Optional category filter (e.g. "chocolates", "beverages") max_price: Optional maximum price filter (not available for OFF data) limit: Number of results to return (default 10, max 50)

Inputs: query (required), category, max_price, limit. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored 2026-05-29 06:25 across 6 tools

Disambiguation5/5

Each tool has a distinct purpose: real-time availability, comparison, feed conversion, schema generation, detailed product info, and search. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using underscores. Examples: check_availability, compare_products, search_products. No mixed styles.

Tool Count5/5

With 6 tools, the server is well-scoped for its purpose. Each tool covers a core functionality without excess or deficiency.

Completeness5/5

The tool set covers the full lifecycle of product information retrieval: search, details, comparison, availability, schema generation, and feed ingestion. No obvious gaps for the domain.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

agent-commerce
ai.petraport
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
E-commerce & Retail Search
2
https://petraport.ai/api/agent-commerce/v1/mcp
CommerceAIA
ai.commerceai
The E-commerce Marketplace For Every AI Agent. A Governed Catalog Of 600M+ US Products, Plus Four Agent Ready Capabilities Search, Price Comparison, Product-Vs-Product, And Detailed Q&A.
E-commerce & Retail Search
11
https://commerceai.ai/mcp/
Osmanth Shop SearchA
com.osmanth
Live product search for AI agents across Shopify merchants and major retailers.
E-commerce & Retail Search
11
https://api.osmanth.com/mcp
CartRelay
market.cartrelay
Live product discovery for AI shopping agents, with shopper-approved retailer handoff.
E-commerce & Retail Search
1
https://cartrelay.market/mcp

Related MCP Servers

ShopGraph
E-commerce & Retail Web Scraping Payments & Billing
laundromatic
A
license
A
quality
B
maintenance
Structured product data from the open web — where platform APIs don't reach. Schema.org + AI extraction. Pay per call via Stripe MPP.
Updated 4 months ago (2026-06-30 03:34 UTC)
2
41 npm
3
Apache 2.0
Nexbidofficial
E-commerce & Retail Agent Orchestration
nexbid-dev
A
license
Not graded
quality
C
maintenance
Agentic commerce infrastructure for AI agents. MCP-native product discovery, contextual ad matching, and purchase facilitation with European privacy compliance (nDSG/GDPR).
Updated 2 months ago (2026-09-04 13:41 UTC)
MIT
Godaloofficial
E-commerce & Retail Search
Godalo-ai
A
license
Not graded
quality
D
maintenance
Affiliate product search for AI agents. Indexes structured merchant feeds — real prices, live stock, affiliate links built in. Works with any MCP client.
Updated 5 months ago (2026-06-04 11:51 UTC)
MIT
dentro MCPofficial
E-commerce & Retail Search
dentro-fyi
A
license
A
quality
D
maintenance
Provides structured commerce data for AI agents, enabling real-time product searches and brand discovery across 22,000+ DTC brands without scraping or hallucination.
Updated 6 months ago (2026-04-29 12:25 UTC)
5
39 npm
MIT

Agentic Product Protocol MCP Server

The Problem

What This Server Does

Installation

Configuration

Claude Desktop

Claude Code (CLI)

Tools

Example Usage

Why Structured Feeds > Landing Pages

Data Source

More MCP Servers by AiAgentKarl

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

ShopGraph

Nexbidofficial

Godaloofficial

dentro MCPofficial