Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
제작자가 쓴 설명(영어 원문)
Make animated travel-route videos: plan a route, style the animation, render an MP4.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"travelanimator": {
"command": "uvx",
"args": [
"travel-animator",
"mcp",
"--source",
"mcp-registry"
]
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add travelanimator -- uvx travel-animator mcp --source mcp-registry프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"travelanimator": {
"command": "uvx",
"args": [
"travel-animator",
"mcp",
"--source",
"mcp-registry"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"travelanimator": {
"type": "stdio",
"command": "uvx",
"args": [
"travel-animator",
"mcp",
"--source",
"mcp-registry"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 도메인 travelanimator.com 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.3.0)은 2개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv)도 있어야 해요.
같은 카테고리에는: Figma Context MCP, Claude Real Video, Figma MCP Server
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Describe a trip. Get a video of it.
Travel Animator MCP lets an AI assistant plan a route, style the animation and render it to an MP4 on your machine — the route drawing itself as it is travelled, a 3D vehicle following it, map labels, country flags, and the distance badge the mobile app draws on top.
You say: *"Make me a 20-second video of a road trip from Lisbon to Porto to Braga, on
the Terrain map, with a red line and a car."*
Your assistant: creates the project, adds the three stops, follows real roads between
them, sets the map and line style, renders, and hands back the path to the MP4.
More prompts that work — and what it won't do — in examples/prompts.md.
Two commands. The second one is not optional — a stdio MCP server cannot prompt you for credentials, so you log in once in your own terminal.
Claude Code
claude mcp add travel-animator -e TADA_SOURCE=readme -- uvx --from "travel-animator[mcp]@latest" travel-animator mcp
uvx travel-animator login
Claude Desktop, Cursor, VS Code, Codex, or any client that takes JSON
{
"mcpServers": { "travel-animator": { "command": "uvx", "args": ["--from", "travel-animator[mcp]@latest", "travel-animator", "mcp"], "env": { "TADA_SOURCE": "readme" } } } }
…then uvx travel-animator login in a terminal.
@latest re-resolves on every launch, so restarting your client is all an update needs. Without it uvx reuses whatever it first cached, and you stay on that version.
TADA_SOURCE tells us which instructions you followed. Optional — delete it if you like.
Already have Python? pip install "travel-animator[mcp]" and use travel-animator as the command. Python 3.12+.
Per-client instructions, including the "works in the terminal but not in the desktop app" PATH fix, are in docs/clients.md.
| Python | 3.12 or newer |
| Account | The same Travel Animator account as the mobile app. A free account can log in, browse the catalogues and author a project — only a premium account can render one. |
| Platform | macOS (Apple silicon), Linux (x86-64, arm64), Windows (x64). These are the four wheels published; other platforms — including Intel macOS — are not supported. |
| Disk | The wheel is ~85 MB. It carries its own Java runtime and, on macOS and Windows, its own graphics driver — there is nothing else to install. Linux uses the system GLES driver, or Mesa for software rendering. |
| Network | Rendering is not offline: map tiles, glyphs and sprites are fetched as frames are drawn, then cached under ~/.cache/tada/render. |
If your machine can't render at all, the server says so up front — before you build a project it can't finish — and can fall back to a server-side render.
list_maps). One is free; the rest need premium.list_models). 11 are free.list_line_styles).MERCATOR or a 3D GLOBE with stars, a sun and a moon.create_project → create_route → update_animation_state → render_video → await_render → MP4
Two things worth knowing, because they change how your assistant behaves:
project_id. There is no "current project", so an assistant can hold several trips open without confusing them.$XDG_STATE_HOME/tada-render/projects/ / (~/.local/state/… if unset). Videos land in that project's renders/; the newest five per project are kept and older ones pruned. Close your assistant and the project is still there tomorrow.30 tools. Full reference with parameters in [docs/tools.md](docs/tools.md).
| Group | Tools |
|---|---|
| Check first | get_capabilities · auth_status |
| Projects | create_project · list_projects · get_project · delete_project · import_project · export_project |
| Route | create_route · get_route · add_point · update_point · remove_point · clear_route · set_real_route |
| Look & feel | get_animation_state · update_animation_state · list_maps · list_models · list_line_styles |
| Render | estimate_render · render_video · await_render · get_render_progress · get_render_result · cancel_render |
| Account sync | list_account_routes · save_project_to_account · load_account_route · delete_account_route |
Renders report progress as they go. render_video returns immediately with a session id; await_render waits on it and, if the render is still going, returns a line your assistant reads out — frames done, percent, time left — and waits again. A ten-minute render is not a ten-minute silence.
Routes sync to the phone. save_project_to_account puts a route in the mobile app's Saved Routes. It carries waypoints only — the reply's dropped list names what didn't survive (avatars, effects, extra model slots, local media, the animation settings), and your assistant should tell you rather than report a clean save.
The full policy — covering the apps, the website and this package — is at travelanimator.com/privacy-policy; it has a section of its own for the MCP server and CLI. What follows is that section in brief.
Usage analytics are opt-in and off until you turn them on. Nothing is collected before that, and nothing at all is collected outside the MCP server.
travel-animator analytics status # what is set, and what it covers
travel-animator analytics on # grant consent travel-animator analytics off # revoke, effective immediately
Never collected — unconditionally, whatever your consent says: route coordinates, place labels, route annotations, file paths, your media, the contents of any route you save or load, the names you give projects, and what a tool returned. *A route records where somebody has actually been.*
Collected with consent: which tools were called, in what order, how long they took and whether they failed; render settings (resolution, duration, animation style, map, vehicle); the *number* of points in a route and the set of countries it crosses.
One free-text exception: when an assistant asks for a tool this server doesn't have, the sentence it writes describing what it was trying to do is collected with that request (up to 2048 characters) — that is the only way a server learns which capability it is missing. It is never attached to an ordinary tool call. Analytics are processed in the United States by a third-party provider.
The MCP server is one of two front ends. The CLI is the other:
travel-animator login # log in: magic link, or a bearer token for CI
travel-animator logout # remove credentials stored on this machine travel-animator analytics # show, grant or revoke analytics consent travel-animator render-bundle # render a prepared render bundle to MP4 travel-animator mcp # run the MCP server (needs the mcp extra)
render-bundle renders bundles produced by the Travel Animator service; it does not create them. The MCP server is the only path that goes from nothing to a finished video.
| Symptom | Cause | Fix |
|---|---|---|
| Tools fail with a "log in" message | No credential on this machine, or it expired | travel-animator login in a terminal, then retry |
| Login works, rendering is refused | Free account | Rendering needs premium |
| Server doesn't start from a desktop app | GUI apps don't inherit your shell PATH | Use the absolute path from which uvx |
pip install fails on your Mac | Intel macOS has no wheel | Apple silicon, Linux or Windows only |
| Render fails on a machine with no GPU | No usable GL | Call get_capabilities first; use the server-side fallback |
| Second render refused | One render at a time, per project and per process | Wait, or cancel_render |
More, including error codes, in docs/troubleshooting.md.
Open an issue — please include your OS, travel-animator --version, your MCP client, the tool that failed and its error_code. Or email connect@travelanimator.com.
This is not open-source software. The travel-animator package ships under a limited use licence: you may install and run it unmodified to prepare and render Travel Animator content and to talk to Lascade's services. You may not redistribute it, modify it, or build a competing service with it. The full terms ship inside the package at tada_render/LICENSE.
Bundled fonts, flag artwork and the libraries inside the renderer are third-party works under their own licences, listed in tada_render/THIRD-PARTY-NOTICES.md. For redistribution or modification rights, contact Lascade.
The documentation and examples *in this repository* are MIT — see LICENSE.
PyPI · travelanimator.com · Privacy · iOS · Android