Get the reviews on a pull request
AI agents call get_pull_request_reviews to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing pull request review data. It performs no creation, modification, deletion, or execution of code. The action is purely informational, consistent with Read category operations like 'get' and 'fetch'. The blast radius of misuse is minimal—an agent could only retrieve review information already accessible within the repository's authorization scope.
From the tool's definition Tool name 'get_pull_request_reviews' and description 'Get the reviews on a pull request' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the reviews on a pull request. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for get_pull_request_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 GitHub MCP Server. Nothing to install.
get_pull_request_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 get_pull_request_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 get_pull_request_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.
get_pull_request_reviews is provided by the GitHub MCP Server MCP server (tuanle96/mcp-github). 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 →