AI agents call chem.compound to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a chemical database (NIH PubChem) and returns reference data about compounds. It performs a lookup operation with no side effects—no data is created, modified, deleted, or executed. The pay-per-call settlement mechanism does not change the tool's function. This is a straightforward Read operation.
From the tool's definition 'Look up a chemical compound' and 'Returns canonical structural identifiers + physical properties' indicate retrieval of existing data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Look up a chemical compound by cid, name, smiles, or inchikey. Returns canonical structural identifiers + physical properties from NIH PubChem. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for chem.compound: 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 Mcp. Nothing to install.
chem.compound 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 chem.compound 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 chem.compound. 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.
chem.compound is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →