AI agents use approve_pr to create or update resources in Bitbucket — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket environment.
This tool creates or modifies data (PR approval status) in a reversible manner—approvals can be removed or changed. It does not execute code, destroy data, or involve financial transactions. The medium severity reflects that misuse could inappropriately gate code reviews or bypass intended approval workflows, affecting code quality and security practices, but the action itself is reversible and scoped to a single PR.
From the tool's definition Tool name 'approve_pr' and description 'Approve a pull request' indicate a write operation that modifies pull request state/metadata in Bitbucket.
Attacks that exploit this kind of access
Approve a pull request. It is categorised as a Write tool in the Bitbucket MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bitbucket MCP server in PolicyLayer and add a rule for approve_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 Bitbucket. Nothing to install.
approve_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 approve_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 approve_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.
approve_pr is provided by the Bitbucket MCP server (javimaligno/mcp-server-bitbucket). 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 →