Closes a pull request with an optional comment and optional branch deletion. Returns structured data with PR number, state, URL, and deleted-branch flag.
AI agents call pr-close to permanently remove resources in Cargo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a PR is an irreversible state change (a closed PR cannot be automatically reopened to its prior state in most workflows), and optional branch deletion is explicitly destructive and unrecoverable. The combination of PR closure and branch deletion makes this a Destructive action with high severity, as it can permanently remove code history and block ongoing work.
From the tool's definition Closes a pull request with an optional comment and optional branch deletion
Documented attack patterns abuse exactly the kind of access pr-close gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cargo, and nothing reaches the server without passing your rules. This is the rule we recommend for pr-close:
{
"version": "1",
"default": "deny",
"hide": [
"pr-close"
]
} pr-close disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Closes a pull request with an optional comment and optional branch deletion. Returns structured data with PR number, state, URL, and deleted-branch flag. It is categorised as a Destructive tool in the Cargo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cargo MCP server in PolicyLayer and add a rule for pr-close: 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 Cargo. Nothing to install.
pr-close is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pr-close 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 pr-close. 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.
pr-close is provided by the Cargo MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cargo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Cargo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.