rc_generate_diagrams · RC Engine MCP: Risk & Policy

WHAT IT DOES

What rc_generate_diagrams does on RC Engine

AI agents use rc_generate_diagrams 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 rc_generate_diagrams needs a policy

The tool creates new diagram artifacts (HTML/Mermaid files) in a designated directory. This is a reversible write operation - the files can be modified or deleted without cascading consequences. It does not execute arbitrary code, trigger external operations with uncontrolled effects, delete data irreversibly, or move money.

From the tool's definition Tool generates and saves diagram files to rc-method/diagrams/ directory. Description states 'Saves to rc-method/diagrams/.' This is file creation/writing without destruction or side effects on other systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rc_generate_diagrams Rate-limited

rc_generate_diagrams 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": {
    "rc_generate_diagrams": {
      "limits": [
        {
          "counter": "rc_generate_diagrams_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 rc_generate_diagrams

What does the rc_generate_diagrams tool do? +

Generate architecture diagrams from the task list. Produces 3 Mermaid-based HTML diagrams: dependency graph (task DAG), Gantt timeline (build schedule), and architecture layers (swimlane view). Requires rc_sequence to have been run first (needs task list in rc-method/tasks/). Saves to rc-method/diagrams/. After success: diagrams are viewable in any browser. 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 rc_generate_diagrams? +

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

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

Can I rate-limit rc_generate_diagrams? +

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

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

rc_generate_diagrams 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.