This record as markdown: /tools/dkeeno-github-mcp-server/github-close-pr.md
What github_close_pr does on Github
AI agents use github_close_pr to create or update resources in Github, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Github environment.
Why github_close_pr is rated Medium
Closing a PR modifies data (PR status) reversibly and does not delete or destroy data. It is a write operation with medium severity because it affects repository workflows and collaboration, but the action is undoable and does not directly delete data or trigger code execution.
From the tool's definition Tool closes (modifies state of) a PR without merging. This is a reversible state change to a GitHub pull request—the PR can be reopened.
Attacks that exploit this kind of access
The rule that runs github_close_pr safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For github_close_pr, this is the rule to start with:
github_close_pr stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every github_close_pr call is checked against it from then on.
Questions about github_close_pr
Close a PR without merging. It is categorised as a Write tool in the Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Github MCP server in PolicyLayer and add a rule for github_close_pr: 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. Nothing to install.
github_close_pr is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the github_close_pr 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_close_pr. 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_close_pr is provided by the Github MCP server (dkeeno/github-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
This server
Across the catalogue