Popcraft MCP
OfficialProvides access to ByteDance's Seedance video generation models (including Seedance 2.0, 2.0 Fast, 2.0 Mini, and 2.5) and the official Seedance 2.5 prompt optimizer, enabling text-to-video, image-to-video, and other video creation workflows through the Popcraft MCP server.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Popcraft MCPMake a 10-second cinematic product teaser and preview the credit cost first."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
https://popcraft.ai/api/mcpQuick start
Every client connects the same endpoint; only the "add server" step differs. The first tool call opens the Popcraft sign-in in your browser — press Allow once and the connection stays live with automatic token refresh. New accounts get 100 free credits.
Client | Setup | Guide |
Claude (web / desktop) | Settings → Connectors → Add custom connector → name | |
Claude Code |
| |
Cursor | Add to | |
ChatGPT | Settings → Apps & Connectors → Advanced → Developer mode on → Create → name | |
Codex | Paste: "Help me connect the Popcraft MCP at https://popcraft.ai/api/mcp — add it as a streamable HTTP server named popcraft, then walk me through the sign-in." | |
Anything else (OpenClaw, Hermes, your own agent) | Streamable HTTP + OAuth 2.1 with discovery metadata and dynamic client registration — the URL alone is enough |
{
"mcpServers": {
"popcraft": {
"url": "https://popcraft.ai/api/mcp"
}
}
}Try it
Paste any of these into a fresh chat once the connector is on:
Use the Popcraft MCP to make a 10-second cinematic product teaser — preview the credit cost first.
Make me a 15-second vertical UGC ad for my product on Popcraft — hook people in the first second. (loads the
ugc-adskill)
I need a YouTube thumbnail for my video about why cheap mechanical keyboards beat expensive ones — make it pop, using Popcraft. (loads the
thumbnail-proskill)
Shoot a brand image set for the citrus soda — hero can, lifestyle scene, pattern tile — then voice a 15-second tagline.
Related MCP server: ShotFlow MCP Server
What your agent gets
Group | Tools | What they do |
Create |
| Text-to-video, image-to-video, first/last frame, reference- and audio-driven videoEvery frontier image model, edits with referencesTTS, sound effects, music3D generationCurated video effectsPlayable voice samples |
Enhance |
| Topaz 2×/4×, nine modes2×/4× with fps controlRe-render a Seedance 2.5 draft at 1080p3D post-processing |
Media & references |
| Signed direct upload — shell recipes, so a 200 MB reference streams from disk, not through the context windowAny public URL → referenceInteractive file pickerSmall files without a shellVerify an upload landedYour media libraryReusable characters and styles |
Jobs & catalog |
| Capabilities, reference limits, aspect ratios, durations and credit costs per modelResult cards that refresh themselves — no polling loopsRevisit and chain past resultsFile results into projects |
Skills |
| Production playbooks served live from the server — see belowPer-step reference modules |
Account |
| Credits and plan before spendingPlans and one-click top-upEvery charge and refund |
Skills, served live
Ask for a deliverable rather than an asset and the agent loads the matching production recipe before it generates anything. Nothing to install, nothing to paste.
ugc-ad— one vertical 9:16 creator-style ad, up to 15 s, with speech and sound rendered natively in the clip.intake → creator identity → script → storyboard → realism pass → cost preview → one Seedance 2.0 clip → QAthumbnail-pro— click-optimised YouTube / Instagram thumbnails with an identity lock for your own face.16 concept frameworks → one intake question → 11-block prompt → parallel variants → micro-edits → 4K upscaleh3-product-ad— minimalist, typography-led product ad on Hailuo 3, 5–15 s, with a native score.intake → copy → three anchor photos → storyboard → cost preview → one generation → QAvoiceover— narration that does not sound like TTS: voice lock, words-per-second budget, per-line direction.script rewrite → voice pick → line-by-line delivery tagssd25-prompting/sd25-prompting-zh— ByteDance's official Seedance 2.5 prompt optimizer, served verbatim (English and Chinese editions); compiles your brief and references into one submission-ready prompt.gpt-image-25-prompting/h3-prompting— model-specific prompt formats for GPT Image 2.5 (change-vs-preserve structure) and Hailuo 3 (structured format with sound and speech fields).
Cost preview on every spend
Every generate tool accepts get_cost: true and returns the exact credit price without submitting anything. Rates come from popcraft_models_explore; the numbers below are as of 2026-09-25 and apply before plan discounts.
Video model | Credits / second (720p) | Image model | Credits / image |
Seedance 2.0 Mini | 14 | Seedream 4.0 | 5 |
Seedance 2.0 Fast | 20 | GPT Image 2.5 Fast | 10 |
Seedance 2.0 | 26 | GPT Image 2.5 | 11 |
Seedance 2.5 · 480p draft | 42 · 24 | Nano Banana 2 | 15 |
Veo 3.1 Fast · Veo 3.1 | 15 · 58 | Nano Banana Pro · 4K | 20 · 35 |
Kling 3.0 Omni | 16 | ||
Wan 3.0 · Hailuo 3 | 20 |
Pro and Max include a daily Seedance 2.0 Fast & Mini allowance at no credit cost, and Nano Banana / Seedream images are unlimited from Plus upward — see unlimited-ai-video and pricing.
How a good agent run looks
Pick the model —
popcraft_models_explore: read itsreference_limits, thevideo_input/image_input/audio_inputenvelope, durations and aspect ratios.Get references in —
popcraft_media_import_urlfor anything with a public URL; otherwisepopcraft_media_uploadand run the returned shell recipe (curl -T file "<proxy_upload_url>"). Pre-check each file against the envelope — an out-of-envelope reference is rejected, or worse, wastes credits.Bind references in the prompt with the model's tokens —
Image 1,Video 1,Audio 1for the Seedance family;<Picture 1>for Hailuo 3.Preview, then spend —
get_cost: true, show the number, then generate. The result card refreshes itself; do not poll in a loop.Chain — any result URL is a valid
medias[].valuefor the next call: upscale it, animate it, edit it.
Recipes
Each recipe is a complete run — the tool calls, the prompts and the outputs, shown inline.
# | Recipe | What you get |
01 | The | |
02 |
| |
03 | Timestamped shot list, 480p draft, then | |
04 | Packshot → lifestyle → background swap → poster → product loop, with the brand's exact wordmark | |
05 | N products × K scenes in one loop, with consistency rules and cost math |
FAQ
This server cannot be deployed
Maintenance
Related MCP Connectors
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Multi-model AI image and video generator. 14 models behind one OAuth-secured MCP endpoint.
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnables agents to create AI music videos and audio-reactive visuals from songs through MCP, including style discovery, music search, rendering, webhook registration, and media management.1MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate professional storyboards and videos from scripts or creative descriptions via MCP-compatible clients.20 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI clients like Claude and ChatGPT to generate images and videos, animate images, create lip-synced videos, list TTS voices, and manage media via remote MCP tools.-
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible clients to generate and upscale AI images, videos, music, and sound effects, manage generation jobs, access model catalogs, and track credits.3MIT