{
  "markdown": "# Asset Factory\n\n[![npm version](https://img.shields.io/npm/v/asset-factory-mcp.svg)](https://www.npmjs.com/package/asset-factory-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![GitHub stars](https://img.shields.io/github/stars/ZionHopkins/asset-factory-mcp.svg?style=social)](https://github.com/ZionHopkins/asset-factory-mcp)\n\nAgentic pipeline that transforms ideas to revenue — for solo founders and bootstrappers.\n\n```bash\nnpx -y asset-factory-mcp\n```\n\n\n![Asset Factory Demo](https://github.com/ZionHopkins/asset-factory-mcp/releases/download/untagged-475ca324e940ae1c1a8c/demo.gif)\n\n---\n\n## Why Asset Factory?\n\nMost MCP servers give you one tool. A GitHub integration. A database query. A Slack bot.\n\nAsset Factory gives you **42 tools that work as a pipeline** — the entire playbook from raw idea to validated revenue, running inside the AI client you already use.\n\n- **No more blank-page paralysis.** Start with `scout` and the system tells you exactly what to do next, every step of the way.\n- **Every stage feeds the next.** Buyer research flows into offer design. Offer design flows into campaign copy. Campaign copy flows into validation. Nothing is wasted.\n- **Math before assets.** Unit economics are validated before you build anything. You'll never spend weeks building an offer that can't work at your budget.\n- **Test ideas for $50, not $5,000.** `rapid_test` gives you signal in 3-5 days with a landing page and paid traffic — before you commit to the full pipeline.\n- **Your AI becomes a co-founder, not a chatbot.** It doesn't just answer questions. It executes a structured business system with you.\n\n---\n\n## Install\n\n```bash\nnpm install -g asset-factory-mcp\n```\n\nOr run directly without installing:\n\n```bash\nnpx -y asset-factory-mcp\n```\n\n## Quick Start\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"asset-factory\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"asset-factory-mcp\"],\n      \"env\": {\n        \"ASSET_FACTORY_PROJECT_DIR\": \"/path/to/your/project\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to your MCP settings (`.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"asset-factory\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"asset-factory-mcp\"],\n      \"env\": {\n        \"ASSET_FACTORY_PROJECT_DIR\": \"/path/to/your/project\"\n      }\n    }\n  }\n}\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/ZionHopkins/asset-factory-mcp.git\ncd asset-factory-mcp\nnpm install\nnpm run build\nnode dist/index.js\n```\n\n## How It Works\n\nAsset Factory is a **two-layer tool system**:\n\n**Layer A — 42 SOP Tools** (read-only): Each tool validates prerequisites against `pipeline-state.json`, loads upstream context from previous stages, checks `learnings.json` for patterns, and returns full SOP instructions enriched with that context. Your AI executes the instructions.\n\n**Layer B — 3 Utility Tools** (mutations): `update_pipeline_state`, `save_asset`, `capture_learning`. These handle all state writes and file creation. Your AI calls them after executing each SOP.\n\n## The Pipeline\n\n```\nFive entry points:\n\n1. scout            → Full pipeline (research → offer → build → deploy → validate)\n2. rapid_test       → Quick $50-100 test (signal in 3-5 days)\n3. passive_deploy   → Marketplace assets (after research)\n4. tournament       → Batch-evaluate 3-5 ideas through Layer 1 simultaneously\n5. portfolio_triage → Rank existing pipelines by profit velocity, select top N\n```\n\n### Full Pipeline Flow\n\n```\nLAYER 1 (Strategist):\n  scout → autonomy → market_intel → research → build_blocks → stress_test → unit_economics\n\nLAYER 2 (Builder):\n  name_lock → platform + product → deploy → qa → validate_prep\n\nLAYER 3 (Validator):\n  validate_check (daily) → validate_decide → feedback → iterate\n\nTRAFFIC (Paid):\n  traffic_strategy → channels → creative_test → funnel_optimize → scale\n\nORGANIC GROWTH (runs parallel with paid):\n  content_engine → content_repurpose → seo_check (monthly)\n\nBOLD ACTION (post-QA):\n  bold_action → credibility compression playbook\n\nREVENUE PHASE MANAGEMENT (optional overlay):\n  portfolio_triage → revenue_review (weekly)\n  Phases: Signal → Cash → Repeat → Scale\n\nCROSS-CUTTING:\n  status | daily_check | lessons | voice_extract | dream_100 | tournament\n```\n\nEach tool checks prerequisites automatically. If you try to run `research` before completing `market_intel`, you'll get a clear STAGE_BLOCKED message telling you exactly what to run first.\n\n## Tools Reference\n\n### SOP Tools (42)\n\n| Tool | Description | Prerequisites |\n|------|-------------|---------------|\n| `scout` | Market scanning — takes a raw idea, determines viability | None (entry point) |\n| `autonomy` | Agent Autonomy Score — AI-buildable product viability | scout |\n| `market_intel` | Deep market research with competitive scoring | scout, autonomy |\n| `research` | Therapeutic Buyer Engine — deep persona research | market_intel |\n| `build_blocks` | 7 Building Blocks from buyer research | research |\n| `stress_test` | Offer scoring across 10 dimensions | build_blocks |\n| `unit_economics` | CPA, LTV, break-even modeling | stress_test |\n| `name_lock` | Lock business/product name | stress_test, unit_economics |\n| `platform` | Tech stack selection and scoring | stress_test |\n| `product` | Product architecture design | stress_test, name_lock |\n| `deploy` | Sales pages, emails, ad copy generation | name_lock, platform, product |\n| `qa` | 7-check persona alignment gate | deploy |\n| `validate_prep` | Validation deployment package | deploy, qa |\n| `validate_check` | Daily 60-second health check | validate_prep |\n| `validate_decide` | End-of-window verdict | validate_prep |\n| `feedback` | Performance diagnosis and fix routing | deploy |\n| `traffic_strategy` | Traffic channel research and scoring | deploy |\n| `channels` | Channel setup and configuration | traffic_strategy |\n| `creative_test` | Ad creative variation testing | channels |\n| `funnel_optimize` | CRO testing across conversion funnel | channels |\n| `scale` | Systematic scaling of validated channels | creative_test |\n| `traffic_analytics` | Performance reporting and attribution | channels |\n| `dream_100` | Relationship strategy and outreach | research |\n| `passive_deploy` | Marketplace asset scoring and specs | research |\n| `passive_check` | Scheduled performance checks | passive_deploy |\n| `passive_compound` | Deploy related assets around anchors | passive_deploy |\n| `passive_portfolio` | Quarterly portfolio review | passive_deploy |\n| `rapid_test` | Quick idea test — landing page + ads | None (entry point) |\n| `rapid_check` | Daily metrics vs. thresholds | rapid_test |\n| `rapid_graduate` | Graduate test to full pipeline | rapid_check |\n| `rapid_status` | Dashboard of all rapid tests | None |\n| `status` | Pipeline status report | None |\n| `daily_check` | 5-minute daily operations pulse | Live campaigns |\n| `lessons` | Pattern library — capture and retrieve | None |\n| `voice_extract` | Brand voice extraction from content | qa |\n| `content_engine` | Topic cluster research, SEO/GEO content generation | qa, validate_prep |\n| `content_repurpose` | Single-pass multi-platform content repurposing | content_engine |\n| `seo_check` | Monthly SEO/GEO audit with AI citation tracking | content_engine |\n| `tournament` | Batch-evaluate 3-5 ideas through Layer 1 | None (entry point) |\n| `bold_action` | Bold Action Playbook — highest-leverage irreversible credibility move | qa |\n| `portfolio_triage` | Rank pipelines by Profit Velocity Score, enforce active cap | None (entry point) |\n| `revenue_review` | Weekly revenue phase assessment (Signal → Cash → Repeat → Scale) | None (entry point) |\n\n### Utility Tools (3)\n\n| Tool | Description |\n|------|-------------|\n| `update_pipeline_state` | Update pipeline-state.json with dot-notation paths |\n| `save_asset` | Save files to assets/[market-name]/ directory |\n| `capture_learning` | Capture reusable patterns to learnings.json |\n\n## Project Directory Structure\n\nAsset Factory creates and manages files in your project directory:\n\n```\nyour-project/\n├── pipeline-state.json      # Pipeline progress tracking\n├── learnings.json            # Pattern library across pipelines\n└── assets/\n    └── [market-name]/\n        ├── research/         # Scout reports, buyer research, market intel\n        ├── building-blocks/  # The 7 Building Blocks\n        ├── product/          # Product Architecture Blueprint\n        ├── copy/             # Sales letters, email sequences\n        ├── campaigns/        # Landing pages, ad copy\n        ├── traffic/          # Traffic strategy, creative tests, analytics\n        ├── validation/       # Deployment packages, daily checks, verdicts\n        ├── voice/            # Brand voice calibration\n        ├── passive-portfolio/ # PADA outputs\n        ├── rapid-test/       # Rapid test assets\n        ├── bold-action/      # Bold Action playbook\n        └── content/          # Organic growth engine outputs\n            ├── pillar/       # 2,000-4,000 word guides\n            ├── spokes/       # 1,000-2,000 word pages\n            ├── repurposed/   # Multi-platform assets per source\n            ├── schema/       # JSON-LD files\n            ├── seo-config/   # robots.txt, sitemap, brand signals\n            └── audits/       # Monthly SEO/GEO audit reports\n```\n\n## Configuration\n\nThe project directory is resolved in order:\n1. `ASSET_FACTORY_PROJECT_DIR` environment variable\n2. `--project-dir=` CLI argument\n3. Current working directory\n\n## First Use\n\nWhen you run `status` with no existing pipeline, you'll see:\n\n> **Three paths available:**\n> 1. **rapid_test** — $50-100 paid traffic test in 3-5 days\n> 2. **scout** — Full active pipeline with deep research and validation\n> 3. **passive_deploy** — Marketplace assets (requires research first)\n\n## Best Practices\n\n### Getting Started\n\n- **Start with `status`** — always run this first. It reads your pipeline state and tells you exactly where you are and what to do next.\n- **New idea? Use `rapid_test` first** — don't run the full pipeline on an unvalidated idea. Spend $50-100 to get signal in 3-5 days. If it graduates, then run `scout`.\n- **One pipeline at a time** — you can run multiple rapid tests in parallel, but focus on one full pipeline at a time. Context switching kills momentum.\n\n### During the Pipeline\n\n- **Follow the order** — the prerequisite system exists for a reason. Each stage feeds the next. Skipping `market_intel` means `research` has no competitive context. Skipping `stress_test` means you might build assets for a broken offer.\n- **Don't skip `qa`** — it catches promise-product misalignment, unattributed statistics, and persona drift. Every asset that touches a buyer must clear the QA gate.\n- **Run `daily_check` every day** during validation — it takes 60 seconds and catches problems before they burn budget.\n- **Use `lessons` after every major decision** — verdicts (ADVANCE/KILL), graduated rapid tests, creative test winners. The pattern library makes every future pipeline smarter.\n\n### Working with the AI\n\n- **Let the AI execute the full SOP** — each tool returns complete instructions. Don't interrupt midway. Let it finish the research, generate the deliverables, and save the files.\n- **Review Tier 3/4 decisions carefully** — the system will pause and ask for your input on market selection, pricing, kill decisions, and anything involving real money. These pauses are intentional.\n- **Trust the math** — `unit_economics` will tell you if the numbers work at your budget. If the verdict is NON-VIABLE, don't try to force it. Move on or adjust the offer.\n\n### Scaling\n\n- **Validate before you scale** — `scale` requires proven creative winners with 30+ conversions. Scaling unvalidated campaigns is the fastest way to burn money.\n- **Compound your learnings** — passive assets that reach ANCHOR status should trigger `passive_compound`. One proven asset can spawn 5-10 related assets.\n- **Run `traffic_analytics` weekly** — attribution drift happens. What worked last week may not work next week. Stay on top of the data.\n\n### Common Mistakes to Avoid\n\n- **Don't build assets before `stress_test` passes** — a GO verdict means the offer is structurally sound. REVISE or REBUILD means fix the foundation first.\n- **Don't skip `name_lock`** — changing the business name after assets are built means rebuilding everything. Lock it early.\n- **Don't ignore KILL signals** — if rapid test metrics hit kill thresholds, kill it. If validation says KILL, capture the lessons and move on. Sunk cost is not a strategy.\n- **Don't publish without `qa` clearance** — unvetted copy with unattributed claims or persona misalignment damages trust and conversion rates.\n- **Don't run the full pipeline for every idea** — that's what `rapid_test` is for. Test 5-10 ideas cheaply, then invest the full pipeline in the winner.\n\n## Revenue Phase System (New in v1.2.0)\n\nOptional overlay that tracks revenue progression through four phases:\n\n| Phase | Goal | Gate to Advance |\n|-------|------|-----------------|\n| Signal | Get intent expressed | Email signup, deposit, DM response |\n| Cash | Close first sale | First payment received |\n| Repeat | Close 3+ at same price | 3 cumulative sales |\n| Scale | Hit target MRR | Sustained monthly revenue |\n\n**How to enable:** Run `portfolio_triage` to select active pipelines. Selected pipelines get `revenue_phase: \"signal\"`. Run `revenue_review` weekly to track progress.\n\n`scout` now includes a **Sales Cycle Reality Check** that estimates days-to-first-sale per market (GREEN <=14d, YELLOW 15-30d, RED >30d). This feeds into the Profit Velocity Score used by `portfolio_triage`.\n\n## Automated QA Test Suite (New in v1.1.0)\n\nThe pipeline includes an automated QA test suite that runs at 3 points:\n\n| Gate | When | What It Catches |\n|------|------|----------------|\n| **Pre-Deploy** | Before `deploy` generates assets | Missing research, broken unit economics math, placeholder text |\n| **Post-Deploy** | After assets written, before `qa` | HTML issues, exposed API keys, email subject length, missing CTAs |\n| **Post-QA** | After persona corrections | Structural issues introduced by corrections |\n\nTest modules in `qa-tests/`:\n- `test_landing_page.py` — HTML structure, CTA presence, secret detection\n- `test_campaign_assets.py` — Email/ad validation, brand consistency\n- `test_research_report.py` — Section completeness, citation density, contradiction detection\n- `test_unit_economics.py` — Margin positivity, CAC/LTV ratio, math verification\n\n**Requires:** Python 3.10+\n\n## Listings\n\nListed on [MCP Server Hub](https://mcpserverhub.net/) | [MCP Registry](https://registry.modelcontextprotocol.io)\n\n## License\n\nMIT\n",
  "bytes": 14726,
  "sha": "b700a89118760477599b7d0d9cb379b130f24f3cd73aeb88ce4d5f7886058429",
  "repo_slug": "zionhopkins/launch-engine-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_zionhopkins_launch_engine_30ed28ad/readme"
}