Record what you did with a paper so surveyHelper remembers it.
AI agents use mark_paper to create or update resources in surveyHelper — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your surveyHelper environment.
This tool creates or modifies state within the surveyHelper system by recording user actions on papers. It does not retrieve data (Read), execute external code (Execute), irreversibly delete data (Destructive), or handle financial operations (Financial). The impact is limited to local state management within the research tool, with low blast radius if misused by an agent—it would only create incorrect usage records.
From the tool's definition Tool description states 'Record what you did with a paper so surveyHelper remembers it' — the verb 'record' indicates data creation/modification.
Attacks that exploit this kind of access
Record what you did with a paper so surveyHelper remembers it. It is categorised as a Write tool in the surveyHelper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the surveyHelper MCP server in PolicyLayer and add a rule for mark_paper: 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.
mark_paper is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mark_paper 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 mark_paper. 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.
mark_paper 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 →