Connection key

Make videos in Antigravity

Connect Idea to Motion to Antigravity and you can ask for a video the same way you ask for anything else. Antigravity 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 speaks Streamable HTTP directly, so connecting is one config entry carrying an API key in an Authorization header.

1Mint a connection key below.
2Add the config entry to your client and reload it.
3Connect a voice key, then ask for a video in chat.

01Connect Antigravity

Generate a connection key if this client needs one, then add the server.

Pick your app

Chat apps

Editors & IDEs

Terminal

Set up Antigravity

Generate a key, then add the server.

Docs

Generate a connection key

Checking your account…

Add it to Antigravity

~/.gemini/antigravity/mcp_config.json

{
  "mcpServers": {
    "ideatomotion": {
      "serverUrl": "https://api.ideatomotion.com/mcp",
      "headers": {
        "Authorization": "Bearer vai_YOUR_KEY"
      }
    }
  }
}

Generate a key above to replace vai_YOUR_KEY.

Open it from the agent panel: … → MCP Servers → Manage → View raw config.
Antigravity uses serverUrl, not url. Restart after saving.

Where the config lives

The exact names Antigravity reads, and what happens when one of them is wrong.

Antigravity reads its MCP servers from a JSON file — ~/.gemini/antigravity/mcp_config.json. The entry goes under mcpServers, with the endpoint in serverUrl. Those names are not what every other client uses, and getting one wrong is not an error, it is silence: the file parses, Antigravity starts, and the server never appears.

Config file: ~/.gemini/antigravity/mcp_config.json
Format: JSON
Root key: mcpServers
Endpoint field: serverUrl
Your key: Written into the file as an Authorization header
Fastest route: Hand-edit the file below, or let the agent write it for you
After saving: Reload or restart Antigravity — MCP config is read when the client starts

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.

Loading…

What Antigravity can actually do

Where the line between your assistant and the platform falls, and why it falls there.

Ask for a video from Antigravity's agent panel the same way you ask for a change to the code — the tool calls run beside your editor, and you approve the plan there.

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.

All 31 MCP tools

A worked example

Type it into the agent panel, in the same thread you use for code.

“Make a 45-second widescreen explainer about how our API rate limiting works.”

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 Antigravity

The ways this goes wrong, and most of them go wrong silently.

You cannot find the file, or the entry looks right and does nothing

Open it from the agent panel: … → MCP Servers → Manage → View raw config. Antigravity picks up MCP servers on launch, so restart after saving before deciding the entry is wrong. The likeliest cause is the endpoint field: Antigravity takes serverUrl, so an entry copied from Cursor or Claude Code carries a url it will quietly ignore.

Antigravity starts fine and the server never appears

Check the names in ~/.gemini/antigravity/mcp_config.json. The entry belongs under mcpServers, and the endpoint goes in serverUrl. These differ between clients — some read mcpServers, some servers, some context_servers — and a wrong one is not an error: the file parses, Antigravity starts, and the server is simply never loaded. Copy the snippet in step 1 rather than adapting one from another client's documentation.

It says it cannot connect, or every tool call comes back 401

A key that is wrong, truncated or revoked gets a 401, and most clients report that as a failed connection rather than as an auth problem. Keys are shown once and stored hashed, so there is no way to read an old one back — generate a fresh one in step 1, then paste the new key over the old one in the config and reload Antigravity. Paste the whole vai_ string including the prefix; the old key can be revoked from the same panel.

You saved the config and nothing changed

~/.gemini/antigravity/mcp_config.json is the file Antigravity reads for this; a copy anywhere else is never opened. Create it if it does not exist yet, keep the surrounding JSON valid — a trailing comma takes the whole file down, not just this entry — and reload Antigravity, which reads MCP config at startup.

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 Antigravity. Silent motion graphics need no voice key at all, so "make it a silent motion graphic instead" is a valid way past this.