Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WAR10CK222/creatomate-mcp-server --skill creatomate-mcpgit clone --depth 1 https://github.com/WAR10CK222/creatomate-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/war10ck222/creatomate-mcp-server/creatomate-mcp)<a href="https://agentmods.dev/skills/war10ck222/creatomate-mcp-server/creatomate-mcp"><img src="https://agentmods.dev/badge/skills/war10ck222/creatomate-mcp-server/creatomate-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/war10ck222/creatomate-mcp-server/creatomate-mcp"><img src="https://agentmods.dev/badge/skills/war10ck222/creatomate-mcp-server/creatomate-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00120 | $0.02740 |
| Opus 5.5 | $0.00048 | $0.01096 |
| Sonnet 5.5 | $0.00024 | $0.00548 |
| Haiku 4.5 | $0.00012 | $0.00274 |
Grade A, and why
creatomate-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| [templates-and-integration.md](references/templates-and-integration.md) | build templates with dynamic fields; hand developers SDK/curl code | How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creatomate MCP: production guide
Use this skill to produce on-brand, professional content with Creatomate and keep a findable record of everything you publish. The server does the heavy lifting: composing, validating, previewing, rendering, and the asset ledger. This skill tells you how to work: plan, build, check, render, record.
0. Preflight (always)
- Are the
creatomate_*tools available? If not, read references/setup.md and help the user connect the server. Stop until it works. - Call
creatomate_workspace_overviewonce per session. Note:- brand kits
- recent campaigns
- pending/failed/expiring assets
- budget and confirmation thresholds
api_key.valid
- Never put API keys or tokens in files, code you show, or chat.
- Renders cost credits. Say so before anything over a few credits; the server enforces confirmations.
1. Start from state (first match wins)
| Situation | Do this |
|---|---|
| The user points at something that exists ("the Black Friday promo", a URL, a render id, "last week's reel") | creatomate_search_assets / creatomate_get_assets first. Never rebuild what already exists. See asset-library. |
| An edit to an existing asset ("make it punchier", "change the price", "square version") | Change only what was asked: creatomate_render with from_asset_id + modifications or variants (keeps lineage). |
| A template or integration request (developers, automations, "reusable") | templates-and-integration |
| Rows of data, "one per product/city/row" | variants-and-batches |
| New content | Brief → plan → build (sections 2–3). Ask at most 3 short questions if platform, length or brand are unknown; otherwise choose sensible defaults and say what you chose. |
2. Routine or hero? (decide first)
| Kind | Examples | How |
|---|---|---|
| Routine: recurring, on-brand, at volume | daily reels, weekly promos, product cards, captioned clips, resizes, data batches | creatomate_compose with the brand kit. Consistency is a feature for brand teams. Vary it on purpose with layout, style and variation (omit variation for a fresh take; reuse the returned one to reproduce). |
| Hero: flagship, campaign launch, "make it stand out" | launch film, brand anthem, big-sale hero, anything the user calls important | Do NOT stop at a recipe. Start from creatomate://examples/* (or examples/) or a blank source and write the RenderScript with a specific concept. Iterate with creatomate_preview (look, critique, change one thing, preview again). Still creatomate_validate before every render. Read creative-direction. |
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 4.2 KB
- examples/captioned-talking-head-9x16.json 2.5 KB
- examples/collage-promo-1x1.json 14 KB
- examples/countdown-sale-story.json 13 KB
- examples/product-card-1x1.json 3.7 KB
- examples/promo-reel-9x16.json 20 KB
- examples/quote-card-4x5.json 2.7 KB
- examples/real-estate-tour-16x9.json 25 KB
- examples/voiceover-explainer-9x16.json 7.6 KB
- examples/youtube-thumbnail.json 2.3 KB
- references/animation-and-transitions.md 2.1 KB
- references/asset-library.md 2.4 KB
- references/brand-kits.md 1.4 KB
- references/captions-and-voiceover.md 2.2 KB
- references/cost-and-safety.md 2.1 KB
- references/creative-direction.md 3.9 KB
- references/pitfalls.md 2.7 KB
- references/renderscript-essentials.md 2.5 KB
- references/scene-planning.md 2.5 KB
- references/setup.md 3.2 KB
- references/templates-and-integration.md 2.1 KB
- references/typography-and-layout.md 2.6 KB
- references/variants-and-batches.md 1.7 KB
- scripts/verify-output.mjs 3.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago First seen · 125 lines · 120 tokens per session scan A e23c72c16864
creatomate-mcp is a skill published in the GitHub repository WAR10CK222/creatomate-mcp-server (1 stars, last pushed 23d ago), licensed MIT. It adds 120 tokens to every session and 2,740 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
creatomate-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creatomate-mcpWAR10CK222/creatomate-mcp-server | Skill | 1 | 23d ago | MIT | A | 120 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |