Medium Risk

bb_create_pull_request

Create a new pull request in a Bitbucket repository

How to control bb_create_pull_request ↓

What bb_create_pull_request does on MCP Bitbucket Python

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

Medium Risk

Why bb_create_pull_request needs a policy

Pull request creation is a reversible write operation that adds metadata and proposes changes to a repository without directly executing code or permanently deleting data. While it can trigger workflows or reviews, the primary action is creating a proposal artifact. It is categorized as Write rather than Execute because the tool itself does not run code—it merely creates a request object.

From the tool's definition Tool creates a pull request: 'Create a new pull request in a Bitbucket repository'. Creating a pull request modifies repository state by introducing a new changeset proposal that is reversible (pull requests can be declined, closed, or reverted).

Documented attack patterns abuse exactly the kind of access bb_create_pull_request gives an agent:

How to control bb_create_pull_request

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Bitbucket Python, and nothing reaches the server without passing your rules. This is the rule we recommend for bb_create_pull_request:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bb_create_pull_request": {
      "limits": [
        {
          "counter": "bb_create_pull_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

bb_create_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.

  1. Create a free account and register MCP Bitbucket Python — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about bb_create_pull_request

What does the bb_create_pull_request tool do? +

Create a new pull request in a Bitbucket repository. It is categorised as a Write tool in the MCP Bitbucket Python MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on bb_create_pull_request? +

Register the MCP Bitbucket Python MCP server in PolicyLayer and add a rule for bb_create_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 MCP Bitbucket Python. Nothing to install.

What risk level is bb_create_pull_request? +

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

Can I rate-limit bb_create_pull_request? +

Yes. Add a rate_limit block to the bb_create_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 bb_create_pull_request completely? +

Set action: deny in the PolicyLayer policy for bb_create_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 bb_create_pull_request? +

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

Enforce policy on every MCP Bitbucket Python tool call.

Start from MCP Bitbucket Python, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

10 MCP Bitbucket Python tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.