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 krusemediallc/cursor-ad-agent --skill clone-video-ad-seedance-arcads-mcpgit clone --depth 1 https://github.com/krusemediallc/cursor-ad-agentWrote 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/krusemediallc/cursor-ad-agent/clone-video-ad-seedance-arcads-mcp)<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/clone-video-ad-seedance-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/clone-video-ad-seedance-arcads-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/krusemediallc/cursor-ad-agent/clone-video-ad-seedance-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/clone-video-ad-seedance-arcads-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 | $0.00111 | $0.05894 |
| Opus 5.5 | $0.00044 | $0.02358 |
| Sonnet 5.5 | $0.00022 | $0.01179 |
| Haiku 4.5 | $0.00011 | $0.00589 |
Grade A, and why
clone-video-ad-seedance-arcads-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 2mo 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.
| Hand-rolled curl auth / `.env` HTTP Basic | MCP handles auth — no `.env` needed for generation | How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clone Video Ad — Seedance 2.0 (Arcads MCP)
Clone an existing video ad onto a different product. The agent analyzes the source
ad with the Arcads MCP's arcads_analyze_media tool (Gemini watches the whole
video — dialogue, beats, camera, tone), adapts the structure for the user's
product, and generates a new Seedance 2.0 video via arcads_generate_video_seedance_20.
This is the MCP-native version. It replaces the REST clone-ad sub-skill's
machinery — no .env, no HTTP Basic auth, no presigned-upload plumbing, no
ffmpeg frame extraction, no local whisper transcription, no session-folder
REST calls. The Arcads MCP server handles auth, file upload, and analysis.
REST clone-ad step |
MCP replacement |
|---|---|
ffmpeg extract-frames + read frames + whisper transcribe |
one arcads_analyze_media call (Gemini) |
Hand-rolled curl auth / .env HTTP Basic |
MCP handles auth — no .env needed for generation |
POST /v2/videos/generate (model seedance-2.0) |
arcads_generate_video_seedance_20 |
GET /v1/assets/{id} polling loop |
arcads_watch_asset (status + download URL), with a REST fallback (see Polling) |
| N parallel POSTs for N variations | nbGenerations (1–10) in a single call |
| Session folder / project / add-to-project | nothing — productId auto-selects |
⚠️ Reference files need an explicit upload in remote agent clients. Automatic local-path upload only works in MCP clients with explicit filesystem bridging. In Cursor the MCP server cannot read local disk; passing a local path returns
400 REFERENCE_FILE_NOT_FOUND. You must upload viaarcads_get_upload_url+ an HTTPPUT, then pass the returned S3filePath. See Uploading reference files below.
Tools used (Arcads MCP)
| Tool | Role |
|---|---|
arcads_list_products |
Resolve productId (skip if you already have it; the generate tools auto-select when there's only one product). |
arcads_get_upload_url |
Get a presigned S3 URL for each local reference file (source video, product image). Required in remote agent clients such as Cursor — see Uploading below. |
arcads_analyze_media |
Watch + transcribe the source ad. referenceVideos: ["<s3 filePath>"]. Returns the blueprint in data.generatedText. |
arcads_generate_video_seedance_20 |
Generate the clone. Key params below. |
arcads_watch_asset |
Poll status and get the signed download URL once generated. Primary polling tool; REST fallback below. |
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.
- 2mo ago First seen · 387 lines · 111 tokens per session scan A fd0c6a32da4c
clone-video-ad-seedance-arcads-mcp is a skill published in the GitHub repository krusemediallc/cursor-ad-agent (11 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 5,894 once invoked, about $0.0004 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 2026-08-31.
clone-video-ad-seedance-arcads-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clone-video-ad-seedance-arcads-mcpkrusemediallc/cursor-ad-agent | Skill | 11 | 3mo ago | MIT | A | 111 | Claude Code, Codex |
| RunAPI Media Generatorrunapi-ai/mcp | Skill | 56 | 3d ago | Apache-2.0 | A | 90 | Claude Code |
| RunAPI Model Explorerrunapi-ai/mcp | Skill | 56 | 3d ago | Apache-2.0 | A | 71 | Claude Code |
| distribea-mediaDistribea/distribea-mcp | Skill | 1 | 20d ago | MIT | A | 113 | Claude Code, Codex |
| competitor-creative-auditcreativescope/creativescope-mcp | Skill | 0 | 23d ago | MIT | A | 77 | Codex |
| mobile-ua-creative-strategycreativescope/creativescope-mcp | Skill | 0 | 23d ago | MIT | A | 99 | Codex |
| weekly-inspiration-briefcreativescope/creativescope-mcp | Skill | 0 | 23d ago | MIT | A | 77 | Codex |