Delete a pull request by declining it
AI agents call delete_pull_request to permanently remove resources in Bitbucket Server MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a pull request removes it from the system in a way that cannot be easily undone. While 'declining' a PR is technically a state change, the tool explicitly uses 'delete' terminology and removes the PR from active view/existence. This constitutes an irreversible action affecting collaboration artifacts.
From the tool's definition Tool name 'delete_pull_request' combined with description 'Delete a pull request by declining it' indicates irreversible removal of a pull request object.
Attacks that exploit this kind of access
Delete a pull request by declining it. It is categorised as a Destructive tool in the Bitbucket Server MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Bitbucket Server MCP server in PolicyLayer and add a rule for delete_pull_request: 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 Bitbucket Server MCP. Nothing to install.
delete_pull_request 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 delete_pull_request 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 delete_pull_request. 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.
delete_pull_request is provided by the Bitbucket Server MCP server (maniksi/bitbucket-server-mcp). 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 →