AI agents call get_food_safety_info to retrieve information from Goodbook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only tool that queries and retrieves food safety guidelines from stored PDF files. No side effects, modifications, code execution, or destructive operations are indicated. It fits the Read category pattern of fetching/querying data without side effects.
From the tool's definition Tool retrieves food safety information and hygiene standards from PDF documents. The description uses 'Get' and 'information', indicating data retrieval with no modification or execution capability.
Attacks that exploit this kind of access
Get food safety information and hygiene standards. It is categorised as a Read tool in the Goodbook MCP Server, which means it retrieves data without modifying state.
Register the Goodbook MCP server in PolicyLayer and add a rule for get_food_safety_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 Goodbook. Nothing to install.
get_food_safety_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_food_safety_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_food_safety_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_food_safety_info is provided by the Goodbook MCP server (whenyouarestrange/goodbook-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 →