pipeline_retry_step · Kiln MCP: Risk & Policy

WHAT IT DOES

What pipeline_retry_step does on Kiln

AI agents invoke pipeline_retry_step to trigger actions in Kiln. 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_retry_step needs a policy

The name implies triggering re-execution of a pipeline step, which is an Execute-class action (running/triggering an operation). However, with no description, confidence is low. Given the server context (3D printer control), retrying a pipeline step could affect ongoing print jobs. Severity is medium due to potential impact on physical hardware operations.

From the tool's definition Tool name 'pipeline_retry_step' suggests re-executing a step in a pipeline; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pipeline_retry_step Rate-limited

pipeline_retry_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_retry_step": {
      "limits": [
        {
          "counter": "pipeline_retry_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 Kiln, so you can run agents against it safely.

FAQ

Questions about pipeline_retry_step

What does the pipeline_retry_step tool do? +

pipeline_retry_step. It is categorised as a Execute tool in the Kiln 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_retry_step? +

Register the Kiln MCP server in PolicyLayer and add a rule for pipeline_retry_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 Kiln. Nothing to install.

What risk level is pipeline_retry_step? +

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

Can I rate-limit pipeline_retry_step? +

Yes. Add a rate_limit block to the pipeline_retry_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_retry_step completely? +

Set action: deny in the PolicyLayer policy for pipeline_retry_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_retry_step? +

pipeline_retry_step is provided by the Kiln MCP server (codeofaxel/Kiln). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.