prc_start

Server RC Engine originalrashmi/rc-engine-product-framework

Category Write

Risk class Medium

Parameters 00 required

WHAT IT DOES

What prc_start does on RC Engine

AI agents use prc_start to create or update resources in RC Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RC Engine environment.

WHY IT NEEDS A POLICY

Why prc_start needs a policy

This tool creates a directory and initializes project state, which are write operations (creating new data/structures). It is reversible and has no destructive, financial, or execution implications. Severity is low because it only sets up an initial directory structure and state for a research pipeline.

From the tool's definition Creates the pre-rc-research/ directory and initializes project state

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prc_start Rate-limited

prc_start stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_start": {
      "limits": [
        {
          "counter": "prc_start_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_start

What does the prc_start tool do? +

FIRST STEP of Pre-RC research. Call when the user describes a product idea and you want deep research before building. Creates the pre-rc-research/ directory and initializes project state. Prerequisites: none - this is the entry point. After success: MUST call prc_classify next. Never skip to prc_run_stage without classifying first. It is categorised as a Write tool in the RC Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prc_start? +

Register the RC Engine MCP server in PolicyLayer and add a rule for prc_start: 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_start? +

prc_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit prc_start? +

Yes. Add a rate_limit block to the prc_start 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_start completely? +

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

prc_start 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.