get_pdf
AI agents call get_pdf to retrieve information from OpenReview MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves document content without modification, deletion, or execution. It aligns with the server's stated purpose of enabling users to 'read submissions and reviews.' The empty description prevents higher confidence, but the naming convention and server context strongly suggest a data retrieval function rather than any write, execute, destructive, or financial operation.
From the tool's definition Tool name 'get_pdf' indicates data retrieval. The tool description is empty and uninformative, which lowers confidence.
Attacks that exploit this kind of access
get_pdf. It is categorised as a Read tool in the OpenReview MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenReview MCP Server MCP server in PolicyLayer and add a rule for get_pdf: 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 OpenReview MCP Server. Nothing to install.
get_pdf 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 get_pdf 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 get_pdf. 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.
get_pdf is provided by the OpenReview MCP Server MCP server (michaelqshieh/openreview-mcp). 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 →