Get full PR detail: diff stats, reviewer approvals, changed files.
AI agents call github_pr_detail to retrieve information from Perceptdot 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 information about GitHub pull requests (diff statistics, reviewer approvals, changed files) with no side effects. It performs a read-only operation on existing data. The action verbs are all informational: 'Get' and implicit retrieval of diff stats, approvals, and file lists. There is no creation, modification, deletion, or execution of external operations.
From the tool's definition Tool name 'github_pr_detail' and description 'Get full PR detail: diff stats, reviewer approvals, changed files' indicate retrieval of existing pull request metadata and code diffs without modification.
Attacks that exploit this kind of access
Get full PR detail: diff stats, reviewer approvals, changed files. It is categorised as a Read tool in the Perceptdot MCP Server, which means it retrieves data without modifying state.
Register the Perceptdot MCP server in PolicyLayer and add a rule for github_pr_detail: 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 Perceptdot. Nothing to install.
github_pr_detail 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 github_pr_detail 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 github_pr_detail. 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.
github_pr_detail is provided by the Perceptdot MCP server (perceptdot/percept). 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 →