prc_run_stage · RC Engine MCP: Risk & Policy

WHAT IT DOES

What prc_run_stage does on RC Engine

AI agents invoke prc_run_stage to trigger actions in RC Engine. 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 prc_run_stage needs a policy

This tool executes computational operations within a structured product development pipeline. It runs predefined stages that have side effects (processing, validation, state changes in the pipeline), making it Execute rather than Read.

From the tool's definition Tool is described as 're-run a specific research stage' and performs an automatic execution of pipeline stages when invoked. The tool triggers external operations (stage execution) whose effects depend on which stage argument is provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prc_run_stage Rate-limited

prc_run_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": {
    "prc_run_stage": {
      "limits": [
        {
          "counter": "prc_run_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 RC Engine, so you can run agents against it safely.

FAQ

Questions about prc_run_stage

What does the prc_run_stage tool do? +

Re-run a specific research stage. In normal flow, stages execute automatically when you approve a checkpoint via prc_gate. Use this tool ONLY to re-run a failed or incomplete stage. Valid stages:. It is categorised as a Execute tool in the RC Engine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on prc_run_stage? +

Register the RC Engine MCP server in PolicyLayer and add a rule for prc_run_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 RC Engine. Nothing to install.

What risk level is prc_run_stage? +

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

Can I rate-limit prc_run_stage? +

Yes. Add a rate_limit block to the prc_run_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 prc_run_stage completely? +

Set action: deny in the PolicyLayer policy for prc_run_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 prc_run_stage? +

prc_run_stage is provided by the RC Engine MCP server (originalrashmi/rc-engine-product-framework). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.