AI agents call pr_await_reviews 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 the status of a review process without modifying, creating, or deleting any data. It is a simple status check that returns information to the caller, fitting the Read category. The low severity reflects minimal security risk from querying review completion status.
From the tool's definition Tool is described as 'Non-blocking: checks agent review completion status once and returns immediately.' The verb 'checks' and 'returns' indicate a query operation with no side effects.
Attacks that exploit this kind of access
Non-blocking: checks agent review completion status once and returns immediately. Use after pr_invoke — pass the. 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_await_reviews: 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_await_reviews 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_await_reviews 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_await_reviews. 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_await_reviews 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 →