Plan the route
Name your stops in any order and let the assistant assemble the journey — city to city, trail to trail.
Overview
What is the Travel Animator MCP server?
The Travel Animator MCP server is a Python package — travel-animator on PyPI — that exposes the Travel Animator route-video pipeline to AI assistants over the Model Context Protocol. Install it, sign in once, and an assistant such as Claude or Cursor can plan a route, style the animation and render an MP4 on your own machine, driven entirely by what you type in chat.
MCP is an open standard for connecting assistants to outside tools. Your client starts the server with travel-animator mcp, discovers the tools it offers, and calls them during the conversation — so there is no separate app to learn and no API keys to wire up beyond your Travel Animator sign-in.
It renders the same journeys the mobile app does, from the same account: the animated routes, the 3D vehicle models and the map styles that Travel Animator is built around. If you would rather build videos by hand, the iOS and Android apps cover the same ground without a terminal — adding the stops, picking a vehicle and exporting is a four-step job on the phone.
Choose your workflow
Who should use MCP instead of the mobile app?
Choose MCP if you already work with an AI assistant and want to describe routes, request styling changes and create videos from your computer. You should be comfortable installing Python packages and configuring your assistant’s tools.
Choose the mobile app if you prefer tapping through the route and preview yourself. For a longer film with footage and narration, use the exported map clip in a video editor.
Before committing: confirm your computer can render, check your account and credit balance, then try one short route. Review the stops and styling before authorizing a render. The CLI’s render-bundle command needs a prepared bundle; use MCP to build a project from a description.
Rendering costs: a premium account and credits are required. Each video costs one credit; the same video can be re-rendered within an hour without another charge. A credit may still be used if local rendering fails after preparation.
Review the published package requirements and credit rules before rendering. The mobile Free and Pro comparison describes the app; it is not an MCP credit allowance.
What your assistant can do
One server, the whole job
The MCP server exposes the full pipeline as tools, so an assistant can go from a sentence to a finished video without you opening an editor.
Tune the animation
Adjust how the animation looks and moves — vehicle, route styling, pacing — by asking for changes in plain language.
Render the video
Export an MP4 on your own hardware. libx264 runs anywhere; pass h264_nvenc for NVIDIA encoding.
Install
Running in three steps
Install Python 3.12 or newer before starting. Setup time depends on your computer and MCP client.
- 1
Install the package with the
mcpextraInstall the
mcpextra to include the MCP SDK. Stable releases no longer need the pre-release flag.Terminalpip install "travel-animator[mcp]" - 2
Sign in to your Travel Animator account
Same account as the mobile app. On an interactive terminal this runs a magic-link flow — enter your email, then the 6-digit code. For CI, pass a bearer token instead. Credentials are stored at
~/.config/tada/credentials.jsonwith mode0600.Terminaltravel-animator login - 3
Point your AI client at the server
Add the server to your client's MCP configuration and restart it. Then just ask for a video — the assistant can call
auth_statusto confirm you're signed in before it starts building a trip.MCP client config{ "mcpServers": { "travel-animator-mcp": { "command": "travel-animator", "args": ["mcp"] } } }
Works with
- Claude Desktop
- Claude Code
- Cursor
- Any stdio MCP client
Try it
Things to ask once it's connected
No commands to memorise — describe the trip and the look you want the way you would to a person.
- Animate my Tokyo → Kyoto → Osaka trip as a plane route and render it in 1080p.
- Plan a road-trip route from Dubai to Muscat and give it a cinematic look.
- Re-render that last video with a slower pace and a different vehicle.
- Check whether I am signed in, then render the bundle you prepared earlier.
Command line
The travel-animator CLI
The MCP server is one subcommand of a small console script you can also drive yourself.
travel-animator loginMagic-link sign-in, or store a bearer token for non-interactive use.
travel-animator logoutRemove locally stored credentials. Local only — there is no server-side session revocation yet.
travel-animator render-bundleRender a prepared bundle to MP4. Map assets require an internet connection. Run with --help for the full flag reference.
travel-animator mcpRun the stdio MCP server. Needs the mcp extra.
Before you start
Requirements & good to know
Graphics & video
Platform wheels bundle Java and, on macOS and Windows, graphics drivers. Linux needs a system GLES driver or Mesa. Rendering fetches map assets online.
Platforms
Local rendering supports Apple silicon Macs, Windows x64, and Linux x86-64 or arm64. Intel Macs cannot render locally; MCP can offer server-side fallback on unsupported machines.
Licence
A limited use licence, not an open-source one: install and run it unmodified to prepare and render Travel Animator content. No redistribution, modification or competing services. Contact Lascade for additional rights.
FAQ
Questions, answered
What is the Model Context Protocol?
MCP is an open standard for connecting AI assistants to outside tools and data. A client — Claude Desktop, Claude Code, Cursor — launches an MCP server, discovers the tools it offers, and can then call them on your behalf during a conversation. travel-animator ships one such server, so the route-video pipeline becomes something an assistant can operate directly.
Which AI assistants can use it?
Any client that speaks MCP over stdio. That includes Claude Desktop, Claude Code and Cursor — the configuration is the same JSON block in each, pointing at the travel-animator command with the mcp argument.
Do I need a Travel Animator account?
Yes. Sign in with your Travel Animator account. Free accounts can author projects, but rendering requires premium access and credits.
Where does the rendering happen?
On supported computers, rendering runs locally and fetches map assets online. MCP can offer a server-side fallback when local rendering is unsupported.
Why does pip say it cannot find a matching version?
Use Python 3.12 or newer and check the current installation instructions on PyPI. Stable releases do not require --pre.
Is it open source?
No. travel-animator is published under a limited use licence: you may install and run it unmodified to prepare and render Travel Animator content, but not redistribute it, modify it or build a competing service with it. The full terms ship inside the package, and bundled fonts and flag artwork stay under their own OFL and MIT licences.
Can I use hardware encoding?
Yes. The default encoder is libx264, which runs everywhere; pass --encoder h264_nvenc to render-bundle for NVIDIA hardware encoding.
What data does the MCP server collect?
MCP analytics are optional but enabled by default. Run travel-animator analytics off to disable them. Events include tool usage and render settings; missing-tool requests can include task text. Read the PyPI analytics section for the full data scope.
Prefer taps to prompts?
Travel Animator is a mobile app first — build the same animated routes by hand on iOS and Android, no terminal required.
Get the app
