trigger_pipeline · Bitbucket MCP: Risk & Policy

WHAT IT DOES

What trigger_pipeline does on Bitbucket

AI agents invoke trigger_pipeline to trigger actions in Bitbucket. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why trigger_pipeline needs a policy

This tool executes an external operation (a pipeline) whose side effects are determined by the pipeline configuration and arguments provided. While the tool itself doesn't directly modify code or delete data, it triggers workflows that can have significant consequences (deployments, building artifacts, running tests against production).

From the tool's definition Tool name 'trigger_pipeline' and description 'Trigger a pipeline run' directly indicate execution of external CI/CD operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trigger_pipeline Rate-limited

trigger_pipeline stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "trigger_pipeline": {
      "limits": [
        {
          "counter": "trigger_pipeline_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 trigger_pipeline

What does the trigger_pipeline tool do? +

Trigger a pipeline run. Supports custom pipelines (from. It is categorised as a Execute tool in the Bitbucket MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on trigger_pipeline? +

Register the Bitbucket MCP server in PolicyLayer and add a rule for trigger_pipeline: 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 trigger_pipeline? +

trigger_pipeline is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit trigger_pipeline? +

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

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

trigger_pipeline 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.