Where is the source code for CraftStory?
https://github.com/itseez3d/craftstory-mcp (MIT). The npm package is `@craftstory/mcp`; the product site is https://craftstory.com/mcp/.

@itseez3d
Basic information
MCP server for the CraftStory API: talking-avatar videos from a photo (CraftStory 2.0) and short clips with generated sound (MiniMax H3)

No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
CraftStory is an AI video platform that turns one photo into a talking video: a person in the photo speaks your script with lip-sync, natural gestures and expressions. This MCP server exposes the CraftStory API as tools, so Claude, Cursor and other MCP clients can generate videos for you. Two models: CraftStory 2.0 (talking-avatar videos of any length, up to 30 minutes) and MiniMax H3 (5–15 s clips with generated sound, or lip-synced to your audio).
sk-cs-..., available on plans with API access).claude mcp add --scope user craftstory -e CRAFTSTORY_API_KEY=sk-cs-... -- npx -y @craftstory/mcp
For Claude Desktop or Cursor use command npx, args ["-y", "@craftstory/mcp"] and the same environment variable; a one-click Claude Desktop bundle (.mcpb) is attached to every GitHub release.create_craftstory2_video: a photo (or a custom avatar scene) plus audio clips become a lip-synced video with gestures, portrait or landscape, any length.create_minimax_h3_video: describe a scene and get a 5–15 s clip from one photo, or drive it with your own audio.list_voices: 180+ library voices in 30+ languages, plus voices you cloned in the app; create_audio_clip synthesizes speech from text or uploads a recording.list_avatars: avatars trained in the app are usable from the tools.wait_for_job polls in bounded slices (≤ 55 s per call) so assistants never hang; get_job_status and get_job_result expose progress, failure reasons and refunds.preview_cost returns the credit price; upscale_video renders 1080p (CraftStory 2.0) or 2× (MiniMax H3) as a new job.api.craftstory.com over HTTPS.https://github.com/itseez3d/craftstory-mcp (MIT). The npm package is `@craftstory/mcp`; the product site is https://craftstory.com/mcp/.
Yes. For any client: command `npx`, args `["-y", "@craftstory/mcp"]`, env `CRAFTSTORY_API_KEY`. The README shows the exact JSON for Claude Desktop and Cursor and the one-line `claude mcp add` command for Claude Code.
The server is free. Videos use CraftStory credits exactly like in the app (CraftStory 2.0 from 2.2 credits per second of audio, MiniMax H3 3.3 credits per second); failed jobs are refunded. A plan with API access is required.
CraftStory 2.0: 8–15 minutes per video. MiniMax H3: 1–3 minutes. The `wait_for_job` tool reports progress and returns as soon as the video is ready.
No. The server runs on your machine and sends your key and inputs only to the CraftStory API over HTTPS; nothing is stored locally and no third-party services are called. Privacy policy: https://craftstory.com/privacy/.

Hosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.
QR Planet QR Code MCP Server - Hosted MCP server for QR Planet. Connect AI agents and MCP-compatible clients to create, update, design, route, and analyze dynamic QR Codes using your QR Planet API key.

Generate and edit images, video, audio and 3D from your AI assistant with fal. Discover 1,000+ models, inspect schemas and pricing, and run creative workflows through a hosted MCP server with browser OAuth.
Access 20+ AI video and image models from Google, OpenAI, xAI, ByteDance, and more. Generate and edit videos with Veo 3.1, Sora 2, Seedance, Kling O3, and images with FLUX, Nano Banana, Seedram 4, GPT Image — all in one

Remote MCP server for AI image, video, voice and music generation. Your agent creates and edits images with Nano Banana 2, GPT-Image 2 or FLUX 1.1 Pro, generates video with Veo 3.1 Fast, Seedance 2.5, Kling, MiniMax or W
Comments