// SCAN REPORT

RC Engine

53 tools. 40 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

40 can modify or destroy data

13 read-only

53 tools total

Community server · catalogue entry verified 30/06/2026

How to control RC Engine ↓

TOOL MAP

What RC Engine exposes to your agents

Read (13) Write / Execute (38) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous RC Engine tools

Destructive · High rc_reset This tool permanently deletes stored pipeline state, checkpoints, and markdown files without recovery option. Destructive · High prc_classify Call AFTER prc_start. Classifies the product idea using Cynefin framework (Clear/Complicated/Complex/Chaotic) and activates the appropriate Execute · High design_pipeline This tool executes a comprehensive pipeline with multiple interdependent steps that produce artifacts (design options, wireframes, copy, reports). Execute · High postrc_gate This tool executes a critical control gate that affects product release decisions and pipeline state.

40 of RC Engine's 53 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RC Engine

PolicyLayer is an MCP gateway — it sits between your AI agents and RC Engine, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "prc_classify": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "brand_import": {
    "limits": [
      {
        "counter": "brand_import_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "copy_critique": {
    "limits": [
      {
        "counter": "copy_critique_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register RC Engine — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RC ENGINE →

Instant setup, no code required.

FULL CATALOGUE

All 53 RC Engine tools

DESTRUCTIVE 2 tools

Destructive prc_classify Call AFTER prc_start. Classifies the product idea using Cynefin framework (Clear/Complicated/Complex/Chaotic) Destructive rc_reset Reset RC Method pipeline state. Clears checkpoint store and markdown state file, allowing a fresh rc_start. DE

EXECUTE 9 tools

Execute design_pipeline Run the full Design Intelligence pipeline in sequence: brand_import → design_intake → design_research_brief → Execute postrc_gate [Pro] Final checkpoint - ship/no-ship decision. Call after postrc_scan completes and user has reviewed finding Execute postrc_scan [Pro] Run AFTER building (Phase 6 Forge complete). Scans code for security vulnerabilities, checks monitoring Execute prc_run_stage Re-run a specific research stage. In normal flow, stages execute automatically when you approve a checkpoint v Execute rc_autopilot Run remaining RC Method steps automatically from the current step through Step 8 (Production Hardening). Auto- Execute rc_forge_all Phase 6 (Forge) BATCH MODE. Builds ALL pending tasks from the approved task list in one call, respecting depen Execute rc_init START HERE. Unified entry point for the RC Engine pipeline. Call this when starting a new project, resuming wh Execute rc_validate Phase 5 (Validate). QUALITY GATE before building. Runs 4 automated checks: anti-pattern scan, token budget aud Execute trace_map_findings Run AFTER both building (Forge) and scanning (postrc_scan). Maps Post-RC findings and RC task completions back

WRITE 29 tools

Write brand_import Import brand assets during Phase 1 (Illuminate). Auto-detects colors, fonts, and design tokens from project fi Write copy_generate Generate the full Content Strategy & Copy System: voice/tone, page-level copy with variants, microcopy library Write copy_iterate Iterate on the generated copy system with user feedback. Updates the COPY-SYSTEM.md in place. Optionally targe Write copy_research_brief Generate a Copy Research Brief: VOC phrase bank, awareness mapping, JTBD extraction, objection mapping, compet Write design_intake Run the Design Intake Assessment - the FIRST step of the Design Intelligence pipeline after PRD. Captures comp Write design_iterate Iterate on existing wireframes based on user feedback. Loads the current design spec and regenerates wireframe Write design_research_brief Generate a Design Research Brief during Phase 2 (Define). Analyzes ICP, competitors, and brand constraints to Write design_select Select a design option after reviewing ux_design output. Saves the selected option ID to project state so that Write pdf_export Export project artifacts as a professional, print-ready HTML document. Converts one or more markdown files int Write playbook_generate Generate the Project Playbook / Architecture Decision Record (ARD). Aggregates ALL pipeline outputs - research Write postrc_configure [Pro] OPTIONAL - configure validation policy BEFORE running postrc_scan. Sets: which modules are active (secur Write postrc_generate_observability_spec PRE-FLIGHT tool - run BEFORE RC Method build phase, ideally after rc_define (Phase 2). Generates an observabil Write postrc_override [Pro] Override a specific scan finding when the user accepts the risk. Requires: finding_id (from postrc_scan Write postrc_report [Pro] Generate a formal validation report from scan results. Call after postrc_scan to produce a shareable mar Write prc_gate Submit a checkpoint decision for the current Pre-RC research stage. NEVER call without presenting the checkpoi Write prc_start FIRST STEP of Pre-RC research. Call when the user describes a product idea and you want deep research before b Write prc_synthesize FINAL STEP of Pre-RC. Call ONLY after Gate 3 is approved (all 6 stages complete). Synthesizes all persona rese Write rc_architect Phase 3 (Architect). Defines technical architecture: tech stack, data models, API design, integrations, and in Write rc_compound Phase 8 (Compound). Final phase before ship. Assesses production readiness: NFR compliance, error handling, ob Write rc_define Phase 2 (Define). Generates a Product Requirements Document from user-provided feature descriptions, user stor Write rc_gate Submit user\ Write rc_generate_diagrams Generate architecture diagrams from the task list. Produces 3 Mermaid-based HTML diagrams: dependency graph (t Write rc_import_prerc BRIDGE from Pre-RC to RC Method. Call after prc_synthesize completes and user wants to continue building. Conv Write rc_save PASSTHROUGH MODE ONLY. Save an artifact generated by the host IDE (not by RC Engine tools) into the RC Method Write rc_sequence Phase 4 (Sequence). Auto-generates a sequenced, dependency-ordered task list from the approved PRD and archite Write rc_start Start RC Method WITHOUT Pre-RC research. Use when user wants to go straight to building without the 20-persona Write trace_enhance_prd Assign tracking IDs to every requirement in the PRD. Call after PRD is created (rc_define or prc_synthesize) a Write ux_design Generate visual design options with HTML wireframes. Call after PRD is created (Phase 2+). Produces 1 or 3 des Write ux_generate Generate a UX child PRD (PRD-[project]-ux.md). Call during Phase 2 (Define) if ux_score returned selective or

READ 13 tools

Read copy_critique Self-critique the generated copy system against conversion heuristics. Scores across 7 categories: Clarity (25 Read design_challenge Stress-test design options against 5 lenses: ICP alignment, copy quality, design justification, conversion flo Read postrc_status Check Post-RC validation progress. Read-only, safe to call anytime. Returns: active modules, latest scan ID an Read prc_status Check Pre-RC research progress. Read-only, safe to call anytime. Returns: current stage, completed stages, gat Read prc_stress_test OPTIONAL Pro-tier tool. Call AFTER prc_synthesize to stress-test the product idea before building. Runs a VC-l Read rc_connect Phase 7 (Connect). Verifies that all built components integrate correctly. Reviews forge outputs for API wirin Read rc_forge_task Phase 6 (Forge). Call once per task from the approved task list. Loads the PRD, architecture, and task context Read rc_illuminate Phase 1 (Illuminate). Call after rc_start, passing the user Read rc_pipeline_status High-level overview of the entire pipeline. Read-only, safe to call anytime. Shows token usage totals and regi Read rc_status Check RC Method progress. Read-only, safe to call anytime. Returns: current phase (1-8), gate statuses (approv Read trace_status Check traceability coverage. Read-only, safe to call anytime after trace_enhance_prd. Returns: total requireme Read ux_audit Audit UI code or a screen description against 42 core UX rules plus specialist modules. Call during or after F Read ux_score OPTIONAL - call during Phase 2 (Define) to assess UX complexity. Pass the feature list from the PRD. Returns:

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about RC Engine

Can an AI agent delete data through the RC Engine MCP server? +

Yes. The RC Engine server exposes 2 destructive tools including prc_classify, rc_reset. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through RC Engine? +

The RC Engine server has 29 write tools including brand_import, copy_generate, copy_iterate. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach RC Engine.

How many tools does the RC Engine MCP server expose? +

53 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 40 can modify, create, or delete data.

How do I enforce a policy on RC Engine? +

Register the RC Engine MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every RC Engine tool call.

Deterministic rules across all 53 RC Engine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RC ENGINE →

Instant setup, no code required.

53 RC Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.