Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
AI filmmaking for short dramas: turn scripts into storyboards, consistent characters and AI video.
Pick the AI app you use, then copy the settings.
Passed 4/4 checks · What you ask goes through the maker’s server (dramacanva.com) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
CustomizeConnectors
Copy each value into the field with the same name in Claude, then click Continue
DramaCanvashttps://dramacanva.com/api/mcpClick Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
+ConnectorsDramaCanvas
Use DramaCanvas and tell me what you can do for me, then show me one thing✓ If Claude says it is using DramaCanvas or shows a DramaCanvas tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Plugins+Add custom MCP server
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
DramaCanvashttps://dramacanva.com/api/mcpStart a new chat and pick DramaCanvas from your plugins before typing
Use DramaCanvas and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using DramaCanvas or shows a DramaCanvas tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --transport http --scope user dramacanvas https://dramacanva.com/api/mcpYou should see DramaCanvas listed as connected
Use DramaCanvas and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using DramaCanvas or shows a DramaCanvas tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 2 min
No key, nothing to install
Use DramaCanvas and tell me what you can do for me, then show me one thing✓ If Cursor says it is using DramaCanvas or shows a DramaCanvas tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 2 min
No key, nothing to install
Use DramaCanvas and tell me what you can do for me, then show me one thing✓ If VS Code says it is using DramaCanvas or shows a DramaCanvas tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://dramacanva.com/api/mcpJSON settings are under “For developers” below
Claude Code
claude mcp add --transport http --scope user dramacanvas https://dramacanva.com/api/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"dramacanvas": {
"url": "https://dramacanva.com/api/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"dramacanvas": {
"type": "http",
"url": "https://dramacanva.com/api/mcp"
}
}
}These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
The server asks you to sign in before it lists its tools.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 13, 2026
The registry name was verified against the domain dramacanva.com (the registry checks domain ownership)
Code last changed today
Not applicable: a cloud server run by the owner of dramacanva.com; you don't run code from the repo
Responded in 407 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 4 of 4 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed today, and the latest version (1.0.0) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
In the same category: Figma Context MCP, AutoClip, Next AI Draw.io
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Clip long videos into short clips with covers and captions. Local CLI and MCP.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An AI film maker you can drive from your coding agent. Connect Claude, Codex or Cursor to the DramaCanvas MCP server and turn a script into episodes, storyboards, character looks and generated video on one infinite canvas.
DramaCanvas accounts and API keys are created at dramacanva.com. Free to start; generation uses credits. View pricing at https://dramacanva.com/pricing.
*Pick a style. Write one line. The canvas lays out the rest.*
In Claude.ai or Claude Desktop, add a custom connector with the URL https://dramacanva.com/api/mcp and sign in. No API key needed.
Run the command from configs/claude-code.sh:
#!/usr/bin/env sh
claude mcp add --transport http dramacanva https://dramacanva.com/api/mcp --header "Authorization: Bearer $DRAMACANVA_API_KEY"
Run the command from configs/codex.sh:
#!/usr/bin/env sh
codex mcp add dramacanva --url https://dramacanva.com/api/mcp --bearer-token-env-var DRAMACANVA_API_KEY
For the default profile, add the configuration from configs/cursor.mcp.json:
{
"mcpServers": { "dramacanva": { "url": "https://dramacanva.com/api/mcp", "headers": { "Authorization": "Bearer ${env:DRAMACANVA_API_KEY}" } } } }
For the expert profile, add the configuration from configs/cursor-expert.mcp.json:
{
"mcpServers": { "dramacanva-expert": { "url": "https://dramacanva.com/api/mcp?profile=expert", "headers": { "Authorization": "Bearer ${env:DRAMACANVA_API_KEY}" } } } }
Paste this prompt into your connected client:
Use the script_to_storyboard prompt with this brief: "Two detectives inspect a locked vault under the city library and find a humming brass cylinder."
DramaCanvas home page with the "Let an AI Agent do it · MCP / API" box (tabs: Claude Code, Codex, Cursor, Other).
One production canvas with 126 connected nodes (character references, scene images, shot rows).
The 3D Director Console starter canvas: scene blocking -> 15-second camera rehearsal (grey-box mannequin) -> final "Spring Record" film, with the written brief beside it.
The 3D Director Console editor: camera path, performer mannequin, keyframe timeline, shot sequence.
The default profile provides 22 tools over streamable HTTP at https://dramacanva.com/api/mcp (protocol version 2025-11-25, server name dramacanvas).
| Tool | Description |
|---|---|
get_account | Read the connected DramaCanvas account. Call it first. |
list_models | List available models for image and video generation. |
| Tool | Description |
|---|---|
list_projects | List workspace projects. |
get_project | Get metadata for a project. |
create_project | Create a new project. |
import_script | Import a script into a project. |
list_units | List units and episodes within a project. |
set_unit_shots | Set shot breakdowns for empty units. |
get_unit_workspace | Get workspace context for a unit. |
| Tool | Description |
|---|---|
create_canvas | Create a new infinite canvas. |
link_canvas_to_project | Link a canvas to a specific project. |
canvas_list_node_types | List supported canvas node types and schemas. |
canvas_get_state | Retrieve current canvas state and snapshot hash. |
canvas_read_storyboard | Read storyboard structure and node data from a canvas. |
canvas_apply_ops | Apply operations to canvas objects with snapshot hash validation. |
canvas_create_storyboard | Create storyboard layouts on the canvas. |
get_canvas_link | Get a browser URL to open the canvas. |
canvas_preview_changes | Preview planned canvas edits before applying them. |
canvas_delete_objects | Delete specified objects from the canvas. |
| Tool | Description |
|---|---|
generate_media | Submit media generation requests. Charges credits immediately. |
get_generation | Get status of a single generation task (waitSeconds up to 50). |
wait_generations | Wait for 1–20 generation tasks (mode any/all, waitSeconds 0–50). |
Connect to https://dramacanva.com/api/mcp?profile=expert to enable the expert profile. This profile adds character versions, revising existing shots, assets, the hosted Agent (agent_start, agent_get_run), and timeline rendering. The profile does not grant extra permissions. What a client can call is the profile intersected with the key scopes. Always read tools/list and only call tools that are listed. OAuth scopes include account:read, models:read, projects:read, projects:write, canvas:read, canvas:write, tasks:read, tasks:write, assets:read, assets:write, agent:run, and offline_access.
Read prompts via prompts/list. Each prompt takes a required brief (script or creative brief) and optional canvasId and projectId. character_lookbook and one_click_short_video are listed only in the expert profile.
| Prompt | Description | Argument |
|---|---|---|
script_to_storyboard | Turn a script into episodes and linked storyboards. | brief |
character_lookbook | Build character looks with consistent identity (expert profile). | brief |
batch_first_frames | Generate consistent first frames for storyboard shots. | brief |
one_click_short_video | Delegate a short video production task to the hosted Agent (expert profile). | brief |
DramaCanvas ships ready-made skills for short-drama and storyboard work. Open any of them on the site, or let an agent use them through the expert profile (list_skills, search_skills, get_skill, add_skill, as used by the one_click_short_video prompt). Browse all skills at https://dramacanva.com/skills.
| Skill | What it does |
|---|---|
| Canvas: One sentence to multi-episode scripts & storyboards | For short drama creators: turn one sentence and reference images into multi-episode scripts and storyboards on a canvas. |
| Turn a Novel Story into a Short Drama Script and Storyboard | Give it a story, and it organizes a short drama script and storyboard for you on the canvas. |
| Turn Novels into Short Drama Scripts, Storyboards & Clips | Turn your novel into a short drama script, character visuals, and multiple video clips. |
| Turn Stories Into AI Video Storyboards by the Second | Break your story down by the second, with camera movement, character action, and sound for each shot. |
| Script to Storyboard: Shot List With Angles & Durations | Enter script dialogue, and it generates a shot list with camera angles, framing sizes, and durations. |
| Script to Motion Comic Storyboard: Turn Story Into Shot List | Give it story text, and it generates a shot-labeled storyboard on the canvas for video beginners. |
| Short-drama shot lists that catch continuity errors | Give it a script and it generates a shot list on the canvas that keeps actions coherent for video creators. |
| Turn stories into short-drama storyboards and plan shots | Enter a story outline to generate storyboards and video clips on a canvas—great for short-drama beginners. |
| AI Video Consistency: Lock Character Looks Across Shots | Give it reference images and needs; it creates a character lock sheet on the canvas to help creators keep looks consistent. |
| Unify your short drama's visual style and storyboard images | Enter a script, set the short drama style and character looks on the canvas, and generate image requirements. |
| Story outline to shootable short script with real dialogue | For short drama beginners: enter a story and write a script on the canvas with clear action and dialogue that sounds real. |
| Dialogue Fix: Make Stiff Script Lines Sound Real | For short-drama writers: send a dialogue draft and get natural, lively lines rewritten on the canvas. |
| Short Drama Hero Entrance: Fix First 30 Seconds, 2 Rewrites | For short-drama writers: enter an entrance scene to diagnose and generate two rewritten scripts on the canvas. |
| Video Editing Rhythm: Dialogue Cuts & Transitions | Enter dialogue or plot, and AI maps out shot cuts and transitions for beginners on the canvas. |
generate_media submits and charges credits immediately, without a confirmation step. The key holder is responsible for costs.idempotencyKey of 8–128 characters. Retries reuse the same key and identical arguments.canvas_list_node_types and canvas_get_state before editing. Pass the latest snapshotHash. On a snapshot conflict, re-read, revise, and use a new key.