About Framesail AI
Framesail AI is a remote MCP server for end-to-end production of long-form faceless YouTube videos. It brings scripting, character references, storyboarding, voiceover, and editing into one pipeline while keeping characters and style consistent across shots.
Key features
- 01Analyze references to derive a style
- 02Generate scripts and identify assets
- 03Create character and setting reference images
- 04Produce word-timed voiceovers
- 05Plan shot-by-shot storyboards
- 06Render, assemble, and export video
Use cases
- 01Build a long-form video from a brief
- 02Keep character appearance consistent across shots
- 03Complete voiceover, storyboarding, and video export
MCP support
The remote MCP server exposes video-production workflow tools over Streamable HTTP, with OAuth 2.1 or API key authentication. Tools cover projects, scripts, references, voiceover, storyboards, rendering, and account information.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.framesail.com/mcpclaude mcp add --transport http framesail https://api.framesail.com/mcp{"mcpServers":{"framesail":{"type":"http","url":"https://api.framesail.com/mcp"}}}Open in Cursor{"servers":{"framesail":{"type":"http","url":"https://api.framesail.com/mcp"}}}Open in VS Code{"mcpServers":{"framesail":{"type":"http","url":"https://api.framesail.com/mcp"}}}{"mcpServers":{"framesail":{"serverUrl":"https://api.framesail.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
68This tool takes no parameters.
Details
From the project READMEFramesail MCP Server
Official remote MCP server for Framesail — create long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot.
Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — with characters drifting between tools and style resetting at every export. Framesail replaces the patchwork: the whole pipeline runs in one place and manages your video's context end to end.
Six stages: Style (paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction), Script (write it yourself or generate it in your narrative style), Reference images (auto-generated for every character, place, and prop), Voiceover (one narrator or many characters, with word-level timing), Storyboard (planned scene by scene), and Editor (captions, music, SFX, then export).
No black box: you control every prompt, asset, model, and setting.
This repository documents the hosted server. The service itself is closed-source and runs at:
https://api.framesail.com/mcp
- Transport: streamable HTTP
- Auth: OAuth 2.1 (Dynamic Client Registration + PKCE) or
fsk_API keys - Registry:
com.framesail/framesail(official MCP registry) · Glama connector - Docs: framesail.com/developers · API reference
Connect
claude.ai / Claude Desktop (OAuth — no key handling):
Settings → Connectors → Add custom connector →
https://api.framesail.com/mcp
A browser login opens; approve the consent screen and you're connected.
Claude Code:
claude mcp add --transport http framesail https://api.framesail.com/mcp \
--header "Authorization: Bearer fsk_..."
Cursor / other MCP clients: point at the URL above with an Authorization: Bearer fsk_... header. Create keys on your account page; every connection (OAuth or key) shows up there and is revocable.
What the tools cover
The full production pipeline, as tools — every tool carries a title and safety annotations (readOnlyHint / destructiveHint):
| Stage | Examples |
|---|---|
| Channels & projects | create/list channels, projects, styles |
| Script | generate a script from a brief, scan it into character/environment/object assets |
| References | generate locked reference images per asset, set the art style |
| Voiceover | render word-timed narration (ElevenLabs / MiniMax voices) |
| Storyboard | plan one frame per shot against the locked references |
| Render | animate segments, assemble, export the finished MP4 |
| Account | whoami, credit balance, job status |
Anonymous initialize and tools/list are supported, so directories and health checks can verify the server without an account. Tool calls require authentication.
Access
API & MCP access is available on Framesail's Pro and BYOK plans — see pricing. With BYOK, jobs covered by your own provider keys (OpenAI, Gemini, Anthropic, fal, ElevenLabs, MiniMax) bill zero platform credits.
Support
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.