Get toxicity data including LD50, carcinogenicity, and mutagenicity
AI agents call get_toxicity_info to retrieve information from PubChem MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries toxicological data (LD50 values, carcinogenicity classifications, mutagenicity assessments) with no side effects, data modification, code execution, or destructive operations. It is a read-only informational query against a chemical database.
From the tool's definition Tool name 'get_toxicity_info' and description 'Get toxicity data including LD50, carcinogenicity, and mutagenicity' indicate retrieval of existing safety/toxicology information from PubChem database.
Attacks that exploit this kind of access
Get toxicity data including LD50, carcinogenicity, and mutagenicity. It is categorised as a Read tool in the PubChem MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PubChem MCP Server MCP server in PolicyLayer and add a rule for get_toxicity_info: 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 PubChem MCP Server. Nothing to install.
get_toxicity_info 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 get_toxicity_info 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 get_toxicity_info. 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.
get_toxicity_info is provided by the PubChem MCP Server MCP server (k-lordbodin7/pubchem-mcp-server). 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 →