Cosmetic Regulatory Intelligence

Structured Safety Intelligence for cosmetic formulation.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Check Ingredient: Check a cosmetic ingredient by common name, INCI name, or CAS number. Use when the user asks whether an ingredient such as retinol, niacinamide, phenoxyethanol, or titanium dioxide i
  • Check Formula: Scan a cosmetic formula INCI list for ingredient-level regulatory and safety risk. Use when the user pastes a product label, asks to screen a formula, requests CPSR-style triage, or wan
  • Search Ingredients: Search cosmetic ingredient records by partial name, function, category, or concept. Use when the user needs candidate INCI names for terms like sunscreen, preservative, retinoid, f

What data it sees

Do you need an account

No: the server works without sign-in

Structured Safety Intelligence for cosmetic formulation. Query 38,411 NOAEL records, 68,540 pre-calculated Margin of Safety values, and 25,157 jurisdictional regulatory opinions across 12 markets (EU, US FDA, Korea MFDS, Japan MHLW, ASEAN, Saudi SFDA, Canada, Australia, ECHA SVHC, CA Prop 65, CA TFCA, WA TFCA). Tools: check_ingredient, check_formula, search_ingredients, calculate_mos. v1.1.0: every ingredient response includes full jurisdictional_profile across all 12 jurisdictions.

How to connect

How to connect Cosmetic Regulatory Intelligence to Claude

The server address to paste into Claude settings:

https://cosmetic-regulatory--twohalves.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Cosmetic Regulatory Intelligence to ChatGPT

The server address to paste into ChatGPT settings:

https://cosmetic-regulatory--twohalves.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Cosmetic Regulatory Intelligence to Cursor

The server address to paste into Cursor settings:

https://cosmetic-regulatory--twohalves.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (4)

Raw names from tools/list. Only developers need these.

check_ingredientCheck a cosmetic ingredient by common name, INCI name, or CAS number. Use when the user asks whether an ingredient such as retinol, niacinamide, phenoxyethanol, or titanium dioxide is safe, restricted, banned, sensitizing, endocrine-active, SVHC-listed, or acceptable for cosmetic use. Do not use for full formula scans, exposure-only MoS math, food additive questions, pharmaceutical actives outside cosmetic use, or broad ingredient discovery. The response includes matched identifiers, SCCS/CIR safety evidence, jurisdictional restrictions, NOAEL data, sensitization records, SVHC flags, and any pre-calculated Margin of Safety values.
check_formulaScan a cosmetic formula INCI list for ingredient-level regulatory and safety risk. Use when the user pastes a product label, asks to screen a formula, requests CPSR-style triage, or wants EU/US/multi-jurisdiction flags across many ingredients. Do not use for a single ingredient lookup, a free-text category search, or a custom SCCS Margin of Safety calculation for one ingredient concentration. The response includes normalized ingredient matches, restricted or banned substances, jurisdiction flags, safety notes, and an overall LOW, MODERATE, or HIGH formula risk assessment.
search_ingredientsSearch cosmetic ingredient records by partial name, function, category, or concept. Use when the user needs candidate INCI names for terms like sunscreen, preservative, retinoid, fragrance allergen, humectant, or hyaluronic acid before choosing a specific record. Do not use when the user has an exact INCI/CAS and needs restrictions, NOAEL, or MoS data; use check_ingredient for that. The response includes matching ingredient names, functions or categories where available, safety scores, and regulatory status hints.
calculate_mosCalculate cosmetic Margin of Safety from ingredient concentration and product type. Use when the user provides an ingredient, percentage, and product format and asks for SCCS-style MoS, SED, safe concentration, or exposure assessment. Do not use for regulatory lookup alone, formula batch screening, food/pharma exposure questions, or when concentration is unknown. The response includes NOAEL source, systemic exposure dose, dermal absorption basis, product exposure assumptions, MoS value, and pass/fail threshold assessment.