AI agents call pr_poll_updates to retrieve information from Pr Review without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about pull request updates without creating, modifying, or deleting any data. Polling for updates is a read-only operation with no side effects. The low severity reflects minimal blast radius even if an AI agent repeatedly polls—it only fetches data already accessible via the GitHub API.
From the tool's definition Tool name 'pr_poll_updates' and description 'Poll for new review updates since a timestamp' indicate data retrieval only. The action is to query/fetch updates (comments, commits, status, agents) without modifying state.
Attacks that exploit this kind of access
Poll for new review updates since a timestamp (comments, commits, status, agents). Use include=[. It is categorised as a Read tool in the Pr Review MCP Server, which means it retrieves data without modifying state.
Register the Pr Review MCP server in PolicyLayer and add a rule for pr_poll_updates: 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 Pr Review. Nothing to install.
pr_poll_updates 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 pr_poll_updates 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 pr_poll_updates. 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.
pr_poll_updates is provided by the Pr Review MCP server (thebtf/pr-review-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 →