request_changes · Bitbucket MCP Server MCP: Risk & Policy

WHAT IT DOES

What request_changes does on Bitbucket MCP Server

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

WHY IT NEEDS A POLICY

Why request_changes needs a policy

Requesting changes on a pull request is a reversible write operation that adds a review state/comment to the PR. It does not delete data or execute code, and can be undone by approving or dismissing the review. The blast radius is moderate as it could block merges if misused.

From the tool's definition Request changes on a pull request

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

request_changes Rate-limited

request_changes 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": {
    "request_changes": {
      "limits": [
        {
          "counter": "request_changes_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about request_changes

What does the request_changes tool do? +

Request changes on a pull request. It is categorised as a Write tool in the Bitbucket 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 request_changes? +

Register the Bitbucket MCP Server MCP server in PolicyLayer and add a rule for request_changes: 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 MCP Server. Nothing to install.

What risk level is request_changes? +

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

Can I rate-limit request_changes? +

Yes. Add a rate_limit block to the request_changes 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 request_changes completely? +

Set action: deny in the PolicyLayer policy for request_changes. 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 request_changes? +

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