AI agents call pr_summary 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 and aggregates existing PR review statistics (counts, severity breakdowns, file organization). It performs no write operations, does not execute external code, and has no destructive or financial impact. The statistics gathering is informational only, making it a standard Read operation with low risk.
From the tool's definition Tool name 'pr_summary' and description 'Get PR review statistics' indicate data retrieval only. Actions are: query totals, counts by severity/file—no modifications, deletions, or side effects.
Attacks that exploit this kind of access
Get PR review statistics: total, resolved, unresolved counts by severity and file. 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_summary: 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_summary 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_summary 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_summary. 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_summary 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 →