AI agents use merge_pull_request 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.
Merging a pull request modifies repository state by combining branches and updating commit history. While reversible via Git's revert/reset mechanisms, it is a significant operation that integrates code changes into a protected branch. The severity is high because unintended merges could introduce bugs, security issues, or break production code.
From the tool's definition Tool name 'merge_pull_request' and description 'Merge a pull request' indicate the tool performs a merge operation, which modifies the state of a pull request and integrates code into a target branch.
Attacks that exploit this kind of access
Merge 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 merge_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. Nothing to install.
merge_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 merge_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 merge_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.
merge_pull_request 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 →