retry_pipeline_stage | PolicyLayer

WHAT IT DOES

What retry_pipeline_stage does on Chiro ERP - Issue Pipeline Orchestrator

AI agents invoke retry_pipeline_stage to trigger actions in Chiro ERP - Issue Pipeline Orchestrator. 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 retry_pipeline_stage needs a policy

Retrying a pipeline stage re-triggers execution of specialized AI agents that perform complex operations including code implementation and PR workflows. The 'optional modifications' parameter means the retry may alter behavior compared to the original run. This falls under Execute because it re-runs automated processes with potentially different arguments/configurations.

From the tool's definition 'Retry a failed pipeline stage with optional modifications' — triggers re-execution of an automated AI agent pipeline stage that can analyze requirements, design solutions, implement code, generate tests, and perform code reviews

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_pipeline_stage Rate-limited

retry_pipeline_stage 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": {
    "retry_pipeline_stage": {
      "limits": [
        {
          "counter": "retry_pipeline_stage_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 Chiro ERP - Issue Pipeline Orchestrator, so you can run agents against it safely.

FAQ

Questions about retry_pipeline_stage

What does the retry_pipeline_stage tool do? +

Retry a failed pipeline stage with optional modifications. It is categorised as a Execute tool in the Chiro ERP - Issue Pipeline Orchestrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retry_pipeline_stage? +

Register the Chiro ERP - Issue Pipeline Orchestrator MCP server in PolicyLayer and add a rule for retry_pipeline_stage: 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 Chiro ERP - Issue Pipeline Orchestrator. Nothing to install.

What risk level is retry_pipeline_stage? +

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

Can I rate-limit retry_pipeline_stage? +

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

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

retry_pipeline_stage is provided by the Chiro ERP - Issue Pipeline Orchestrator MCP server (olwalgeorge2/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.