Connect Idea to Motion to VS Code (Copilot) and you can ask for a video the same way you ask for anything else. VS Code (Copilot) 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.
Generate a connection key if this client needs one, then add the server.
Pick your app
Chat apps
Editors & IDEs
Terminal
Generate a connection key
Add it to VS Code (Copilot)
.vscode/mcp.json (per project) or the user mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "ideatomotion-key",
"description": "Idea to Motion API key",
"password": true
}
],
"servers": {
"ideatomotion": {
"type": "http",
"url": "https://api.ideatomotion.com/mcp",
"headers": {
"Authorization": "Bearer ${input:ideatomotion-key}"
}
}
}
}servers here — not mcpServers like other clients.The exact names VS Code (Copilot) reads, and what happens when one of them is wrong.
VS Code (Copilot) reads its MCP servers from a JSON file — .vscode/mcp.json. It can live in either of two places, and the per-project one only applies inside that project. The entry goes under servers, with the endpoint in url. Those names are not what every other client uses, and getting one wrong is not an error, it is silence: the file parses, VS Code (Copilot) starts, and the server never appears.
Narration is synthesized on your own ElevenLabs, Cartesia or Sarvam AI key. Silent motion graphics need none.
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.
Where the line between your assistant and the platform falls, and why it falls there.
Ask for a video from VS Code (Copilot)'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.
Type it into the agent panel, in the same thread you use for code.
“Make a 30-second explainer about what this extension does, for the marketplace listing.”
What comes back
The ways this goes wrong, and most of them go wrong silently.
MCP tools only run in Agent mode; in Ask or Edit mode they are inert. The snippet also uses VS Code's inputs indirection, so the key is prompted for on first use and kept in the secret store rather than in the file — which is what makes a committed .vscode/mcp.json safe. If no prompt ever appears, the id under inputs and the ${input:…} reference in the header have drifted apart.
Check the names in .vscode/mcp.json. The entry belongs under servers, and the endpoint goes in url. These differ between clients — some read mcpServers, some servers, some context_servers — and a wrong one is not an error: the file parses, VS Code (Copilot) starts, and the server is simply never loaded. Copy the snippet in step 1 rather than adapting one from another client's documentation.
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 use the one-click link again, which carries the new key with it and reload VS Code (Copilot). Paste the whole vai_ string including the prefix; the old key can be revoked from the same panel.
This can live in two places: .vscode/mcp.json (per project) and the user mcp.json. A per-project file only applies while you are working in that project, so an entry in the wrong one reads exactly like a config VS Code (Copilot) is ignoring. Put it in the user-level file if you want it everywhere, and reload VS Code (Copilot) either way.
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 VS Code (Copilot). Silent motion graphics need no voice key at all, so "make it a silent motion graphic instead" is a valid way past this.