Make videos in Claude web & Desktop
Connect Idea to Motion to Claude web & Desktop and you can ask for a video the same way you ask for anything else. Claude web & Desktop writes the script, plans each scene and writes the animation code; we synthesize the voiceover, time it to the words, render the animation and hand back an MP4. It connects over OAuth — you paste one URL and approve access, with no key to copy or store.
- 1Add a custom connector and paste the server URL below.
- 2Sign in and approve access when prompted.
- 3Connect a voice key, then ask for a video in chat.
01Connect Claude web & Desktop
Generate a connection key if this client needs one, then add the server.
Pick your app
Chat apps
Editors & IDEs
Terminal
- 1. In Claude web & Desktop, open Settings → Connectors → Add custom connector.
- 2. Paste this URL and save.
- 3. Sign in with your Idea to Motion account and approve access.
https://api.ideatomotion.com/mcp
No key needed — Claude web & Desktop signs in through your browser.
- Settings → Connectors → Add custom connector, then paste the URL.
- You'll be asked to sign in and approve access — no key to copy.
Where the connection lives
The exact names Claude web & Desktop reads, and what happens when one of them is wrong.
There is no file to edit. Claude web & Desktop stores the connector against your account and runs the OAuth exchange itself, so the same connection follows you to every device you sign in on.
- Stored in
- Your Claude web & Desktop account, not a file
- Format
- None — you paste the server URL
- Your key
- Not needed; you sign in and approve in the browser
- Staying connected
- Access tokens last an hour and the connector renews them on its own
02Connect your voice
Narration is synthesized on your own ElevenLabs, Cartesia or Sarvam AI key. Silent motion graphics need none.
Your voice key
Idea to Motion generates the voiceover on your own text-to-speech account. Add an ElevenLabs, Cartesia or Sarvam AI key — it's stored encrypted and never shown again. Rendering is blocked until a key is connected.
What Claude web & Desktop can actually do
Where the line between your assistant and the platform falls, and why it falls there.
Ask for a video in a Claude web & Desktop conversation the same way you ask for anything else — the tool calls run inline and you approve the plan right there in the chat.
- It writes the content — a narrated script, a silent shot list, or a keep-and-drop cut plan for a video you upload — and hands it back for approval. Nothing is produced until you say yes.
- It directs every scene, then writes a self-contained Remotion component for each one. Submitted code is validated and run in a sandbox before it is accepted, so a mistake comes back as a tool error it can fix rather than a broken video.
- It renders stills of its own scenes on our servers and looks at them, which is why it can correct a card sitting across someone's face without you screenshotting anything.
- We do the parts a language model should not be doing: voice synthesis, word-level timing, captions, music, assembly and the final render.
- There is deliberately no export tool. Exporting spends money and picks a quality tier, so it stays a click you make on the platform — and a video you have already paid for re-exports for free.
A worked example
Type it into a normal conversation once the connector is enabled.
“Make a 30-second vertical video explaining what our product does, for Instagram.”
What comes back
- 1It opens a picker: the looks play as short clips, the narrator voices have samples you can hear, and you choose. Clients that cannot draw a panel get the same list as text.
- 2It writes the script and shows it to you. Tell it what to change and it rewrites — the video does not start until you approve.
- 3It directs and writes each scene, checking stills as it goes. This is the long part, and it is mostly quiet: a scene submission legitimately holds its request open while the server renders.
- 4The finished video appears in your projects here. Watch it, ask for adjustments in the same conversation, then export it from the platform.
Troubleshooting Claude web & Desktop
The ways this goes wrong, and most of them go wrong silently.
The sign-in page bounces you back, or the approval never sticks
Approving the connector needs a live Idea to Motion session in the same browser you are approving from. Sign in here first, then add the connector — the approval screen checks both your click and a live session for the same account, so an expired one sends you round the loop again. A private window with no session is the usual cause.
The connector is added but no tools show up in the conversation
Open Claude web & Desktop's connector settings and confirm it is listed as connected rather than pending. Custom connectors are per-account, so a connector added on one account is not there on another. Removing it and pasting the URL again re-runs the whole approval, which is usually faster than debugging it.
A snippet somewhere is asking you for an API key
You never need one here. Claude web & Desktop only accepts a URL and runs the OAuth exchange itself, so if you are looking at a vai_ key and a config file you are following instructions written for a different client. Those keys exist for clients that cannot open a browser.
The tools work but it cannot produce the voiceover
Narration and transcription run on your own ElevenLabs, Cartesia or Sarvam AI key rather than ours, so a narrated or recorded video needs one connected — step 2 on this page, or the set_voice_key tool from inside Claude web & Desktop. Silent motion graphics need no voice key at all, so "make it a silent motion graphic instead" is a valid way past this.