Use this tool when the user asks about the safety, regulatory status, or compliance of a cosmetic ingredient under EU Regulation 1223/2009, US FDA, Korea MFDS, Japan MHLW, ASEAN, Saudi SFDA, Canada Hotlist, Australia SUSMP, ECHA SVHC, California Prop 65, California TFCA, or Washington TFCA. Accep...
Accepts freeform code/query input (query)
Part of the Cosmetic Regulatory Intelligence MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call check_ingredient 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 check_ingredient 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.
tools:
check_ingredient:
rules:
- action: allowSee the full Cosmetic Regulatory Intelligence policy for all 4 tools.
Agents calling read-class tools like check_ingredient have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Use this tool when the user asks about the safety, regulatory status, or compliance of a cosmetic ingredient under EU Regulation 1223/2009, US FDA, Korea MFDS, Japan MHLW, ASEAN, Saudi SFDA, Canada Hotlist, Australia SUSMP, ECHA SVHC, California Prop 65, California TFCA, or Washington TFCA. Accepts common name, INCI name (e.g. 'Retinol', 'Sodium Lauryl Sulfate'), or CAS number (e.g. '68-26-8', '151-21-3'). Returns: SCCS safety opinion, EU Annex II/III/V/VI classification, pre-calculated Margin of Safety (MoS) value, NOAEL reference, dermal absorption, sensitization profile, CIR conclusion, endocrine-disruptor status, ECHA SVHC listing, China IECIC status, and jurisdiction-specific restrictions across 12 regulatory bodies. Backed by 725,921 rows of primary-source-traceable data from rootsbybenda.com. Do not use for general chemistry queries unrelated to cosmetic ingredient compliance.. It is categorised as a Read tool in the Cosmetic Regulatory Intelligence MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for check_ingredient. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Cosmetic Regulatory Intelligence MCP server.
check_ingredient 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 check_ingredient rule in your Intercept 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 Intercept policy for check_ingredient. 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.
check_ingredient is provided by the Cosmetic Regulatory Intelligence MCP server (twohalves/cosmetic-regulatory). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept