Export paper dicts to CSV, RIS, or BibTeX.
AI agents use export_papers to create or update resources in Paper Search — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paper Search environment.
The tool writes academic paper metadata to structured file formats (CSV, RIS, BibTeX), which is a reversible creation/modification action. It has no destructive capability, does not execute arbitrary code, does not move money, and does not delete or overwrite existing data without user consent.
From the tool's definition Tool description states 'Export paper dicts to CSV, RIS, or BibTeX' — this creates/writes data to file formats.
Attacks that exploit this kind of access
Export paper dicts to CSV, RIS, or BibTeX. It is categorised as a Write tool in the Paper Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paper Search MCP server in PolicyLayer and add a rule for export_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 Paper Search. Nothing to install.
export_papers 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 export_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 export_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.
export_papers is provided by the Paper Search MCP server (its-antony/paper-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
export_papers is one line of Paper Search's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →