Get open pull requests with review status, labels, and dates (up to 20).
AI agents call github_prs 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 is a read-only tool that retrieves pull request metadata from GitHub. It has no side effects, does not modify state, and presents minimal risk even if an AI agent invokes it repeatedly. The constraint to 20 results further limits blast radius.
From the tool's definition Tool retrieves 'open pull requests with review status, labels, and dates' — it queries and returns data without modification. The description indicates a fetch/list operation constrained to 20 results.
Attacks that exploit this kind of access
Get open pull requests with review status, labels, and dates (up to 20). 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_prs: 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_prs 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_prs 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_prs. 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_prs 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 →