List comments attached to a specific pull request review
AI agents call get_pull_request_review_comments to retrieve information from Mcp Github 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 comments. It performs no write, delete, execute, or financial operations. The blast radius of misuse is minimal; an attacker could enumerate comments on public or accessible PRs but cannot modify code, delete data, or trigger external actions.
From the tool's definition Tool name includes 'get' and description states 'List comments' — both indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
List comments attached to a specific pull request review. It is categorised as a Read tool in the Mcp Github MCP Server, which means it retrieves data without modifying state.
Register the Mcp Github MCP server in PolicyLayer and add a rule for get_pull_request_review_comments: 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 Mcp Github. Nothing to install.
get_pull_request_review_comments 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_review_comments 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_review_comments. 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_review_comments is provided by the Mcp Github MCP server (@missionsquad/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 →