Agentic Product Protocol Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Agentic Product Protocol Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
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.
This MCP server implements the core ideas of agentic product discovery:
Uses Open Food Facts as a demo data source — works with any product feed.
pip install agentic-product-protocol-mcpOr with uvx (no install needed):
uvx agentic-product-protocol-mcpAdd to claude_desktop_config.json:
{
"mcpServers": {
"product-protocol": {
"command": "uvx",
"args": ["agentic-product-protocol-mcp"]
}
}
}claude mcp add product-protocol -- uvx agentic-product-protocol-mcp| 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 |
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'}"
| 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 |
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.
| 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 |
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.