# Ad Lab MCP server

Agent View of the PolicyLayer registry record for Ad Lab: identity, probed posture, risk grade, and all 13 tools classified. HTML page: https://policylayer.com/tools/577-tools-ad-lab-mcp

## Facts

- Server id: `@577-tools/ad-lab-mcp`
- Install: `npx -y @577-tools/ad-lab-mcp`
- Homepage: https://www.npmjs.com/package/@577-tools/ad-lab-mcp
- Registry record: grade C, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 13
- Tool categories present: Read, Write
- Tags: 577 tools ad lab mcp
- Record last modified: 2026-10-10T10:09:44.527Z

## Tools (13)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `advance_stage` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/advance-stage.md |
| `get_creative` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-creative.md |
| `get_flow_status` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-flow-status.md |
| `get_knowledge_index` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-knowledge-index.md |
| `get_lab_capacity` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-lab-capacity.md |
| `get_product_context` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-product-context.md |
| `get_scoring_rules` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/get-scoring-rules.md |
| `list_external_winners` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/list-external-winners.md |
| `list_losers` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/list-losers.md |
| `list_revision_requests` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/list-revision-requests.md |
| `list_winners` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/list-winners.md |
| `render` | Read | Low | https://policylayer.com/tools/577-tools-ad-lab-mcp/render.md |
| `add_idea` | Write | Medium | https://policylayer.com/tools/577-tools-ad-lab-mcp/add-idea.md |

## Tool descriptions

- `advance_stage` — Move an Ad Lab creative between staff-manageable stages through ad-lab-ingest. READ BEFORE USING
- `get_creative` — Read one Ad Lab creative by id: full Creative Spec, current stage, short_code, status, lineage, freshly signed image URL, and the published_at / stopped_at / scored_at timestamps. Use it to confirm what add_idea created, and to check a c…
- `get_flow_status` — Exact count of a product
- `get_knowledge_index` — Fetch the full distilled adgenius knowledge index (large JSON: global Meta signals, per-product learnings, style clusters).
- `get_lab_capacity` — Free Ad Lab ad-set slots per product. This is the system
- `get_product_context` — Fetch the Ad Lab context bundle for a product: knowledge (product_md, carousel_profile, deep_profile), brand_voice, claim_safety, brand_docs (all brand markdown keyed by slug; READ adgenius-playbook, winning-copy-formulas, winning-ad-sty…
- `get_scoring_rules` — Fetch the live winner/loser bar the scorer actually enforces: minimum ROAS and purchases for a winner (both must clear in the same window), the loser impression floor, and the maturity period before any verdict. Served from the scoring m…
- `list_external_winners` — List LIVE Meta ads that clear the same winner bar as list_winners but have no Ad Lab creative behind them. This is the half of
- `list_losers` — List losing Creative Specs for a product = the NEGATIVE lesson set, what NOT to do. Read the caveats:
- `list_revision_requests` — List a product
- `list_winners` — List winning Creative Specs for a product - Ad Lab creatives the scorer promoted to stage
- `render` — Render an Ad Lab image through the central render edge function.
- `add_idea` — Required final handoff for every finished product ad: add the generated Creative Spec to the Ad Lab Ideas tab, optionally attaching a rendered image. The Creative Spec must include non-empty copy.headline and copy.primary_text.

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=577-tools-ad-lab-mcp · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/577-tools-ad-lab-mcp