List the research lines you're following.
AI agents call list_interests to retrieve information from surveyHelper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user-tracked research interests from local storage. It performs a simple query operation without modifying, executing, or deleting data. The blast radius of misuse is minimal—an attacker could learn what research topics the user is interested in, but cannot alter data or trigger external actions. Confidence is high because the description clearly indicates a read-only list operation.
From the tool's definition Tool name 'list_interests' and description 'List the research lines you're following' indicate a retrieval operation with no side effects. The verb 'list' is a classic read operation that queries existing data.
Attacks that exploit this kind of access
List the research lines you're following. It is categorised as a Read tool in the surveyHelper MCP Server, which means it retrieves data without modifying state.
Register the surveyHelper MCP server in PolicyLayer and add a rule for list_interests: 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 surveyHelper. Nothing to install.
list_interests 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 list_interests 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 list_interests. 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.
list_interests is provided by the surveyHelper MCP server (rich7420/surveyhelper). 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 →