update_pipeline_variable · Bitbucket MCP: Risk & Policy

WHAT IT DOES

What update_pipeline_variable does on Bitbucket

AI agents use update_pipeline_variable 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.

WHY IT NEEDS A POLICY

Why update_pipeline_variable needs a policy

This tool modifies an existing pipeline variable (a reversible change). It does not execute code or workflows (that would be Execute), delete data (Destructive), or handle financial transactions (Financial). Pipeline variables are configuration parameters used in CI/CD, so updating them could affect build/deployment behavior if misused by an AI agent, warranting medium severity rather than low.

From the tool's definition Tool name is 'update_pipeline_variable' and description states 'Update a pipeline variable'. The word 'Update' indicates modification of existing data rather than deletion or creation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_pipeline_variable Rate-limited

update_pipeline_variable 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": {
    "update_pipeline_variable": {
      "limits": [
        {
          "counter": "update_pipeline_variable_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, so you can run agents against it safely.

FAQ

Questions about update_pipeline_variable

What does the update_pipeline_variable tool do? +

Update a pipeline variable. 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.

How do I enforce a policy on update_pipeline_variable? +

Register the Bitbucket MCP server in PolicyLayer and add a rule for update_pipeline_variable: 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.

What risk level is update_pipeline_variable? +

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

Can I rate-limit update_pipeline_variable? +

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

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

update_pipeline_variable 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.