Framedeck

Created By
Lukaris2 months ago
Connect any AI assistant to your content production pipeline. 33 tools for managing video ideas, productions, stages, and frames. Works with Claude, ChatGPT, Gemini, and Copilot.
Overview

framedeck-mcp

MCP server for Framedeck — connect any AI assistant to your content production pipeline.

Works with Claude, ChatGPT, Gemini, Copilot, and any MCP-compatible client.

Quick Start

  1. Get your API key at framedeck.app > Settings > API Keys
  2. Add to your AI assistant config (see below)

Setup

Claude Code

claude mcp add framedeck -e FRAMEDECK_API_KEY=your_key_here -- npx -y framedeck-mcp

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "framedeck": {
      "command": "npx",
      "args": ["-y", "framedeck-mcp"],
      "env": {
        "FRAMEDECK_API_KEY": "your_key_here"
      }
    }
  }
}

Other MCP Clients

Set the environment variable FRAMEDECK_API_KEY and run:

npx framedeck-mcp

Usage Examples

Talk to your AI assistant naturally — here are three end-to-end workflows:

Example 1 — Capture and graduate ideas

You: "I just had 3 video ideas: a knife sharpening tutorial, a Sony A7IV review, and a day-in-the-life vlog. Add them to my idea pool."

Claude (via MCP): Calls create_multiple_cards with the three titles. They land in your Idea Pool's "Ideas" stage.

You: "The knife sharpening one is a go — graduate it to a real production."

Claude: Calls graduate_to_production which creates a new dedicated production with full stages (Idea → Scripting → Filming → Editing → Published) and moves the idea card across.

Example 2 — Plan a production day

You: "For the Sony review, add subtasks: write intro, shoot product shots, record voiceover, edit B-roll, color grade, export final."

Claude: Calls set_active_board to "Sony A7IV review", then create_multiple_cards with all six subtasks in the "Filming" stage.

You: "Mark the intro and product shots as done."

Claude: Calls move_card twice to push them into the "Done" stage.

Example 3 — Get a project overview

You: "How's my channel looking? Anything overdue?"

Claude: Calls get_board_overview for each production. Returns a summary showing card counts per stage, overdue items highlighted in red, and which productions need attention.

You: "What's assigned to me right now?"

Claude: Calls get_my_cards and lists everything you own grouped by board and status.

Tools (32)

ToolDescription
set_active_boardSet the active production context
get_active_boardShow current active production
list_boardsList all productions/projects
create_boardCreate a new production or project
list_columnsList stages in a board
create_columnCreate a new stage
delete_columnDelete a stage
list_cardsList cards/frames with filters
create_cardCreate a card/frame
create_multiple_cardsBatch create (up to 50)
update_cardUpdate title, description, priority, due date
move_cardMove to a different stage
delete_cardPermanently delete
archive_cardSoft delete (restorable)
duplicate_cardCopy with checklist and labels
set_card_colorColor-code a card
add_commentAdd a comment
add_checklist_itemAdd a subtask
toggle_checklist_itemCheck/uncheck a subtask
add_labels_to_cardAdd labels to a card
remove_label_from_cardRemove a label
get_card_detailsFull card info
search_cardsSearch by keyword
assign_cardAssign a team member
get_my_cardsCards grouped by status
get_board_overviewBoard summary with overdue items
list_labelsList all labels
create_labelCreate a label
link_commitLink a git commit to a card
log_workLog time spent
get_sprint_summaryActivity summary
graduate_to_productionPromote idea to full production

Dual Mode

Framedeck supports two board modes:

  • Creator mode: Productions, Stages, Frames — for content pipelines
  • Classic mode: Projects, Stages, Cards — for standard project management

The MCP server automatically uses the correct terminology based on each board's mode.

Idea Pool

When you add ideas without specifying a board, they automatically land in your Idea Pool. When an idea is ready, use graduate_to_production to create a dedicated production with full stages (Idea > Scripting > Filming > Editing > Published).

Safety Annotations

Every tool ships with MCP safety annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) so AI clients can warn users before destructive actions like delete_card, delete_column, and archive_card.

Privacy & Support

License

MIT

Server Config

{
  "mcpServers": {
    "framedeck": {
      "command": "npx",
      "args": [
        "-y",
        "framedeck-mcp"
      ],
      "env": {
        "FRAMEDECK_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Lukaris
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

13 hours ago
Shippo
@Shippo

21 hours ago