Override a card field (e.g. title, summary, year, venue). The correction is
AI agents use correct_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.
The tool modifies existing paper metadata fields (title, summary, year, venue) which is a reversible write/update operation. It does not delete data, execute code, or involve financial transactions. Severity is medium as incorrect overrides could corrupt research data, but changes appear to be reversible corrections to local records.
From the tool's definition Override a card field (e.g. title, summary, year, venue). The correction is
Attacks that exploit this kind of access
Override a card field (e.g. title, summary, year, venue). The correction is. 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 correct_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.
correct_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 correct_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 correct_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.
correct_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 →