github_list_pull_requests
AI agents call github_list_pull_requests to retrieve information from GitHub Code Review Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Listing pull requests is a query operation with no side effects—it retrieves metadata about existing PRs without creating, modifying, deleting, or executing any actions. This is a standard Read category tool. Severity is low because misuse only exposes PR metadata, not secrets or critical data, and has no operational impact on the repository.
From the tool's definition Tool name is 'github_list_pull_requests' indicating a retrieval operation. Description is empty, but the name and server context (code review assistant) make it clear this lists existing PRs without modifying them.
Attacks that exploit this kind of access
github_list_pull_requests. It is categorised as a Read tool in the GitHub Code Review Assistant MCP Server, which means it retrieves data without modifying state.
Register the GitHub Code Review Assistant MCP server in PolicyLayer and add a rule for github_list_pull_requests: 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 Code Review Assistant. Nothing to install.
github_list_pull_requests 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_list_pull_requests 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_list_pull_requests. 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_list_pull_requests is provided by the GitHub Code Review Assistant MCP server (sanjanaspanda/mcp-server). 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 →