AI agents call load_resources to retrieve information from LetsFG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static workflow documentation and guides. It has no side effects, does not modify data, execute external operations, delete anything, or involve financial transactions. It is purely informational and therefore classified as Read with low severity.
From the tool's definition Tool name 'load_resources' and description 'Load the LetsFG workflow guide' indicates retrieval of documentation/reference material. No modification, execution of operations, deletion, or financial transactions occur.
Attacks that exploit this kind of access
Load the LetsFG workflow guide (3-step booking flow, pricing, passenger rules, error handling). It is categorised as a Read tool in the LetsFG MCP Server, which means it retrieves data without modifying state.
Register the LetsFG MCP server in PolicyLayer and add a rule for load_resources: 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 LetsFG. Nothing to install.
load_resources 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 load_resources 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 load_resources. 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.
load_resources is provided by the LetsFG MCP server (letsfg/letsfg). 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 →