pipeline_step · Dobbe MCP: Risk & Policy

WHAT IT DOES

What pipeline_step does on Dobbe

AI agents invoke pipeline_step to trigger actions in Dobbe. 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 pipeline_step needs a policy

This tool advances an automated pipeline state machine, triggering the next step in workflows that can include code changes, test execution, and vulnerability remediation. While it 'submits results', the act of progressing the pipeline causes downstream automated actions to execute, making Execute the most appropriate category. Misuse could cause unintended code modifications or deployments at high blast radius.

From the tool's definition 'Submit results for the current pipeline step and get the next instruction' — drives a state machine executing DevOps workflows including vulnerability resolution, code review, test generation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pipeline_step Rate-limited

pipeline_step 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": {
    "pipeline_step": {
      "limits": [
        {
          "counter": "pipeline_step_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 Dobbe, so you can run agents against it safely.

FAQ

Questions about pipeline_step

What does the pipeline_step tool do? +

Submit results for the current pipeline step and get the next instruction. It is categorised as a Execute tool in the Dobbe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pipeline_step? +

Register the Dobbe MCP server in PolicyLayer and add a rule for pipeline_step: 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 Dobbe. Nothing to install.

What risk level is pipeline_step? +

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

Can I rate-limit pipeline_step? +

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

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

pipeline_step is provided by the Dobbe MCP server (nareshnavinash/dobbe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.