List papers by your state (seen/read/understood/dismissed), or all if omitted.
AI agents call my_papers 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 a filtered list of papers based on the user's specified state or returns all papers if no filter is provided. It performs no mutations, deletions, execution of code, financial transactions, or irreversible operations. It is a straightforward data retrieval function with no blast radius if misused by an AI agent.
From the tool's definition Tool name is 'my_papers' and description states 'List papers by your state' — a query operation that retrieves and returns data without modification or side effects. The verb 'List' is explicitly a Read operation.
Attacks that exploit this kind of access
List papers by your state (seen/read/understood/dismissed), or all if omitted. 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 my_papers: 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.
my_papers 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 my_papers 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 my_papers. 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.
my_papers 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 →