merge_pull_request · Bitbucket Cloud MCP Server MCP

WHAT IT DOES

What merge_pull_request does on Bitbucket Cloud MCP Server

AI agents use merge_pull_request to create or update resources in Bitbucket Cloud MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket Cloud MCP Server environment.

WHY IT NEEDS A POLICY

Why merge_pull_request needs a policy

The merge operation creates new commits (or modifies the commit history) and advances the target branch pointer—effects that are reversible through git operations (revert, reset) but represent significant modification of repository state. This is Write rather than Execute because the tool's primary purpose is data modification (merging code) rather than arbitrary command execution.

From the tool's definition Tool description states 'Merge an open pull request' with support for multiple merge strategies (merge commit, squash, fast-forward). This modifies the repository state by integrating code changes into a target branch.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

merge_pull_request Rate-limited

merge_pull_request stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "merge_pull_request": {
      "limits": [
        {
          "counter": "merge_pull_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Bitbucket Cloud MCP Server, so you can run agents against it safely.

FAQ

Questions about merge_pull_request

What does the merge_pull_request tool do? +

Merge an open pull request. Supports merge commit, squash, and fast-forward strategies. It is categorised as a Write tool in the Bitbucket Cloud MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on merge_pull_request? +

Register the Bitbucket Cloud MCP Server 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 Cloud MCP Server. Nothing to install.

What risk level is merge_pull_request? +

merge_pull_request is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit merge_pull_request? +

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.

How do I block merge_pull_request completely? +

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.

What MCP server provides merge_pull_request? +

merge_pull_request is provided by the Bitbucket Cloud MCP Server MCP server (lexmata/bitbucket-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.