Framedeck MCP is an MCP (Model Context Protocol) server used to connect AI assistants to the Framedeck content production pipeline. It is suitable for YouTube, Instagram, TikTok, and podcast creators, helping manage the content production process through natural language.
Purpose The tool is designed to let users operate the content production board in Framedeck using any MCP-compatible AI assistant (such as Claude, ChatGPT, Gemini, Copilot). Instead of manually clicking through the interface, users complete tasks such as creating ideas, planning production, and tracking progress through conversation.
Main capabilities
- Create cards: Supports creating single or multiple cards, for example batch-adding video ideas.
- Idea graduation: Ideas in the Idea Pool can be graduated to formal production via graduate_to_production, automatically creating a production project containing the complete stages (Idea → Scripting → Filming → Editing → Published).
- Set active board: Switch the currently operated board via set_active_board.
- Move cards: Move cards to different stages via move_card, for example marking a task as complete.
- Board overview: Get a summary of the number of cards, overdue items, etc. for each production via get_board_overview.
- Personal tasks: List all cards assigned to yourself via get_my_cards, grouped by board and status.
- Supports two board modes: Creator mode (Productions, Stages, Frames) and Classic mode (Projects, Stages, Cards); the server automatically uses the corresponding terminology.
- Safety annotations: Each tool has MCP safety annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint), so AI clients can remind users before performing destructive operations such as deleting cards, deleting columns, and archiving cards.
How to use
- Get an API key in framedeck.app under Settings > API Keys.
- Add the MCP server to the AI assistant configuration. For Claude Desktop, it needs to be added to claude_desktop_config.json.
- Other MCP clients: Set the environment variable FRAMEDECK_API_KEY and run the server.
- After that, you can converse with the AI assistant in natural language, for example:
- "I have 3 video ideas: a knife sharpening tutorial, a Sony A7IV review, and a daily vlog. Add them to the idea pool."
- "The knife sharpening one is ready to go—graduate it to formal production."
- "Add subtasks for the Sony review: write the opening, shoot product photos, record voiceover, edit B-roll, color grade, export the final cut."
- "Mark the opening and product photos as complete."
- "How is my channel doing? Is anything overdue?"
- "What tasks are assigned to me right now?"
Applicable scenarios
- Content creators managing production processes for videos, podcasts, etc.
- Quickly updating task status through an AI assistant in team collaboration.
- Projects that need full-process tracking from idea pool to publishing.
Limitations
- Requires a Framedeck account and API key.
- Requires an MCP-compatible AI client.
- Specific feature details, fees, pricing, platform support, etc. are not provided in the materials; please refer to official information.
Privacy and support Privacy policy:https://framedeck.app/privacy Terms of service:https://framedeck.app/terms Support email: support@framedeck.app Issue feedback:https://github.com/Lukaris/framedeck-mcp/issues
