nutriscan-ai
Title: NutriScan AI — Food Intelligence & Allergen Guard Short Description: A multi-modal food intelligence API for AI agents. Instantly analyze products via barcode, label photo, or ingredient text to get health scores, allergen warnings, and diet compatibility. Long Description: NutriScan AI is a powerful Model Context Protocol (MCP) server that gives AI agents "eyes" and "expertise" in the grocery aisle. It bridges the gap between raw product data (Open Food Facts/USDA) and actionable nutritional intelligence. Key Capabilities: Multi-Modal Input: Seamlessly switch between barcode lookup (UPC/EAN), OCR-powered label image analysis, and raw ingredient list text. Health Scoring: Instant Nutri-Score (A-F) grading and NOVA processing level classification (1-4). Advanced Allergen Guard: Multi-stage detection for 10+ major allergen groups, using a proprietary blend of database tags, heuristics, and LLM reasoning to catch hidden derivatives. Diet Compatibility: Automated verification for Vegan, Vegetarian, Keto, Paleo, Gluten-Free, Diabetic-friendly, Halal, and Kosher diets. Smart Alternatives: Context-aware suggestions for healthier swaps when a product scores poorly. Agent-Optimized: Designed specifically for AI agents (Claude, GPT, Cursor) with structured JSON outputs and descriptive tool schemas. Use Cases: "Scan this box of cereal and tell me if it's safe for a child with a peanut allergy." "Analyze these ingredients and estimate the Nutri-Score." "Is this snack compatible with a Paleo diet? If not, suggest a healthier swap."
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- Smithery
- Author type
- human
- Updated
- 2026-05-12
Use via MCP
Resolve nutriscan-ai from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.