Fetch the final accept/reject decision for a submission, if posted.
AI agents call openreview_get_decision to retrieve information from Openreview without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves pre-existing decision information from OpenReview venues (accept/reject status for submissions). This is a read-only query operation with no side effects—it does not create, modify, delete, or execute any actions. The data retrieved is factual information already published by the venue.
From the tool's definition Tool name and description both indicate a retrieval operation: 'Fetch the final accept/reject decision' retrieves existing decision data with no modification capability.
Attacks that exploit this kind of access
Fetch the final accept/reject decision for a submission, if posted. It is categorised as a Read tool in the Openreview MCP Server, which means it retrieves data without modifying state.
Register the Openreview MCP server in PolicyLayer and add a rule for openreview_get_decision: 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. Nothing to install.
openreview_get_decision 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 openreview_get_decision 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 openreview_get_decision. 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.
openreview_get_decision is provided by the Openreview MCP server (opencodice-research/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 →