Use this tool when the user doesn't know the exact INCI name and wants to discover cosmetic ingredients by partial name, function (e.g. 'sunscreen', 'emulsifier', 'preservative', 'surfactant'), or category (e.g. 'humectant', 'UV filter', 'antioxidant'). Returns up to 20 matches per query with INC...
Risk signalsAccepts freeform code/query input (query)
Part of the Cosmetic Regulatory Intelligence server.
Free to start. No card required.
AI agents call search_ingredients to retrieve information from Cosmetic Regulatory Intelligence without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though search_ingredients only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"search_ingredients": {}
}
}See the full Cosmetic Regulatory Intelligence policy for all 4 tools.
These attack patterns abuse exactly the kind of access search_ingredients gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use this tool when the user doesn't know the exact INCI name and wants to discover cosmetic ingredients by partial name, function (e.g. 'sunscreen', 'emulsifier', 'preservative', 'surfactant'), or category (e.g. 'humectant', 'UV filter', 'antioxidant'). Returns up to 20 matches per query with INCI name, CAS number, functional category, safety rating, EU status, and concern level. Fast discovery tool — best for identifying candidate ingredients before deep-diving with check_ingredient. Do not use for known INCI lookups (use check_ingredient directly); do not use for batch compliance (use check_formula).. It is categorised as a Read tool in the Cosmetic Regulatory Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Cosmetic Regulatory Intelligence MCP server in PolicyLayer and add a rule for search_ingredients: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cosmetic Regulatory Intelligence. Nothing to install.
search_ingredients is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_ingredients rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_ingredients. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_ingredients is provided by the Cosmetic Regulatory Intelligence MCP server (twohalves/cosmetic-regulatory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Cosmetic Regulatory Intelligence tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.