获取毒性实验数据
AI agents call get_toxicity_data to retrieve information from PubChem Chemical Safety MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval operation with no side effects. The tool queries and returns toxicity data from an existing database. There is no capability to modify data, execute code, delete records, or commit financial transactions. The worst-case misuse would be information gathering, which has minimal security impact.
From the tool's definition Tool retrieves toxicity experiment data from PubChem database. Description states 'get toxicity' (retrieves data). No modification, deletion, or execution capabilities indicated.
Attacks that exploit this kind of access
获取毒性实验数据. It is categorised as a Read tool in the PubChem Chemical Safety MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PubChem Chemical Safety MCP Server MCP server in PolicyLayer and add a rule for get_toxicity_data: 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 Chemical Safety MCP Server. Nothing to install.
get_toxicity_data 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_data 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_data. 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_data is provided by the PubChem Chemical Safety MCP Server MCP server (liueic/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 →