We only use cookies to enhance your experience. No cross-site tracking, no ads. Read our Cookie Policy.
Add Supercut to VS Code for Copilot-powered workflows over your recordings.
Add the configuration below to .vscode/mcp.json in your workspace. You can also run MCP: Add Server from the Command Palette, choose HTTP, and paste the Supercut MCP endpoint.
{
"servers": {
"supercut": {
"type": "http",
"url": "https://mcp.supercut.ai/mcp"
}
}
}Add to .vscode/mcp.json. Requires GitHub Copilot extension with MCP support. The first time you use the server, your browser opens to sign in to Supercut and authorize access.
Start the Supercut server from VS Code and accept the workspace trust prompt. VS Code opens your browser so you can sign in, choose your workspace, and approve access.
Run MCP: List Servers from the Command Palette and confirm that Supercut is running. Its tools should then appear in the tool picker in Copilot Chat.
MCP: List ServersStart with a read-only request so you can see the recording context your client receives.
Find the Supercut recording linked to this feature and summarize the implementation requirements.Need client-specific troubleshooting? Read the VS Code MCP configuration guide.
How Supercut MCP gives agents permission-aware access to recordings, transcripts, and frames.
Add the Supercut MCP server in Claude Code, then sign in only if Claude asks you to.
Connect Supercut as a remote connector in Claude Desktop and authorize access in the browser.
Point Codex at Supercut’s MCP endpoint and bring recording context into your coding sessions.
Configure Cursor so its agents can search recordings and read transcripts from your editor.