Decline a pull request
AI agents use decline_pull_request to create or update resources in Bitbucket Server MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket Server MCP environment.
Declining a pull request changes its status but does not delete it; the PR and its history remain accessible and the action can typically be reversed by reopening. This is a reversible state change, placing it in the Write category. Misuse could disrupt development workflows by blocking code merges, warranting medium severity.
From the tool's definition 'Decline a pull request' — declining changes the state of a PR to declined/rejected
Attacks that exploit this kind of access
Decline a pull request. It is categorised as a Write tool in the Bitbucket Server MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bitbucket Server MCP server in PolicyLayer and add a rule for decline_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.
decline_pull_request 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 decline_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 decline_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.
decline_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 →