Cire Cosmetic Ingredient Risk Engine

Created By
voix-sys3 months ago
Deterministic INCI safety scoring API for AI agents. Analyze cosmetic ingredient lists for irritation, allergen, pregnancy, acne, and interaction risks. Designed for shopping agents, catalog filters, compliance pipelines, and K-beauty recommendation engines. Returns clean JSON — no markdown, no prose.
Overview

CIRE API — Cosmetic Ingredient Risk Engine

CIRE Certified Version License

Deterministic INCI safety scoring API for AI agents.
Designed for shopping agents, catalog filters, compliance pipelines, and K-beauty recommendation engines.


What is CIRE?

CIRE scores cosmetic ingredient lists (INCI format) for safety risk across 5 categories:

CategoryDescription
irritation_riskSkin irritation potential
allergen_riskKnown allergens
pregnancy_riskIngredients unsafe during pregnancy
acne_riskComedogenic ingredients
interaction_riskDangerous ingredient combinations

Fully deterministic. Rule-based. No ML. Always returns valid JSON.


Quick Start

curl -X POST https://web-production-9cdb4.up.railway.app/v1/analyze \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"inci": "Water, Retinol, Glycolic Acid"}'

Response:

{
  "risk_score": 52,
  "risk_level": "moderate",
  "confidence_score": 65,
  "category_results": { ... },
  "matches": { ... }
}
  • risk_score: 0–100 (higher = safer)
  • risk_level: low / moderate / high
  • confidence_score: evidence strength (0–100)

Authentication

Pass your API key in the X-API-Key header.

X-API-Key: cire-xxxxxxxxxxxx

Get your API key → cire.ai


Pricing

PlanCallsPrice
Starter1,000$9
Growth10,000$49
Scale100,000$299

API Reference

Full interactive docs: /docs

POST /v1/analyze

Analyze an INCI string. Costs 1 credit.

GET /v1/credits

Check remaining credits.


Use Cases

  • Shopping agents — filter products by pregnancy safety, allergen risk
  • Catalog managers — bulk scan thousands of SKUs
  • Compliance pipelines — EU/K-beauty export regulation checks
  • Recommendation engines — rank products by safety profile

Tech

  • Pure Python, zero ML dependencies
  • Deterministic outputs — same input always returns same output
  • Evidence-based: EU restriction list, FDA advisories, CIR reports, peer-reviewed consensus
  • 13/13 smoke tests passing

Built for the AI agent ecosystem. CIRE Certified.

Server Config

{
  "mcpServers": {
    "cire": {
      "command": "python3",
      "args": [
        "mcp_server.py"
      ]
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
voix-sys
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

5 hours ago
Mnemom

6 hours ago