AI agents call feeding_guide to retrieve information from Baselings without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool provides guidance data by querying a reference mapping of food types to stats to job optimization. It is purely informational—the agent reads data to inform decisions but does not itself perform any state changes, execute commands, or move funds. The tool sits in the Read category with low severity due to its informational nature and lack of side effects.
From the tool's definition Tool name 'feeding_guide' and description 'Maps food→stat→job optimization' indicate a lookup/reference function that retrieves mapping information. No mutation, execution, or financial transaction occurs.
Attacks that exploit this kind of access
What food to feed a baseling based on its target job. Maps food→stat→job optimization. It is categorised as a Read tool in the Baselings MCP Server, which means it retrieves data without modifying state.
Register the Baselings MCP server in PolicyLayer and add a rule for feeding_guide: 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 Baselings. Nothing to install.
feeding_guide 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 feeding_guide 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 feeding_guide. 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.
feeding_guide is provided by the Baselings MCP server (jimbo530/baselings-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 →