Get the list of files changed in a pull request
AI agents call get_pull_request_files to retrieve information from GitHub See MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about files modified in a pull request without creating, modifying, deleting, or executing any operations. It is a passive query that returns information only, posing minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_pull_request_files' and description 'Get the list of files changed in a pull request' indicate a retrieval operation with no modification of state. The verb 'get' and 'list' are characteristic of Read operations.
Attacks that exploit this kind of access
Get the list of files changed in a pull request. It is categorised as a Read tool in the GitHub See MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub See MCP Server MCP server in PolicyLayer and add a rule for get_pull_request_files: 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 See MCP Server. Nothing to install.
get_pull_request_files 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_files 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_files. 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_files is provided by the GitHub See MCP Server MCP server (jesusmaster/github-see-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 →