Retrieve chemical safety and hazard data for a substance used in industrial, cosmetic, or food applications, by name or CAS number. Input: chemical name, technical substance name, synonym, or CAS number (e.g. 'bisphenol A', 'formaldehyde', '80-05-7'). Returns: substance identifiers (CAS, EC numbe...
Risk signalsAccepts freeform code/query input (query)
Part of the Chemical Safety server.
Free to start. No card required.
AI agents call check_chemical to retrieve information from Chemical Safety 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_chemical 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": {
"check_chemical": {}
}
}See the full Chemical Safety policy for all 3 tools.
These attack patterns abuse exactly the kind of access check_chemical 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.
Retrieve chemical safety and hazard data for a substance used in industrial, cosmetic, or food applications, by name or CAS number. Input: chemical name, technical substance name, synonym, or CAS number (e.g. 'bisphenol A', 'formaldehyde', '80-05-7'). Returns: substance identifiers (CAS, EC number, PubChem CID, InChIKey, SMILES, molecular formula/weight via crosswalk), ECHA SVHC Candidate List status with reason and inclusion date, NIOSH occupational exposure data (REL, PEL, IDLH, exposure routes, symptoms, target organs, health hazards), GHS classification (signal word, hazard statements, pictograms), ICSC safety card data (short/long-term effects, exposure routes), and cross-references to cosmetic ingredient and food additive databases. Sources: ECHA SVHC Candidate List (253 substances), NIOSH Pocket Guide (677 chemicals), GHS classifications (468,165 records), ICSC safety cards, substance identifier crosswalk (73,252 substances). For chemical hazard assessment and regulatory compliance. Do not use for batch SVHC screening (use check_svhc_list), cosmetic formula checks, food additive safety, or drug interactions.. It is categorised as a Read tool in the Chemical Safety MCP Server, which means it retrieves data without modifying state.
Register the Chemical Safety MCP server in PolicyLayer and add a rule for check_chemical: 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 Chemical Safety. Nothing to install.
check_chemical 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_chemical 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 check_chemical. 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_chemical is provided by the Chemical Safety MCP server (https://chem-mcp-server.rootsbybenda.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Chemical Safety 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.