Use Feedqube in VS Code with GitHub Copilot (MCP)

Add the server

1. Create .vscode/mcp.json in your project (or run "MCP: Open User Configuration" from the Command Palette for all projects).
2. Add Feedqube as below. VS Code asks for the API key the first time and stores it securely, so it is not written in the file.
3. Open Copilot Chat in Agent mode and enable the Feedqube tools.

{
  "inputs": [
    { "type": "promptString", "id": "feedqube-key", "description": "Feedqube API key", "password": true }
  ],
  "servers": {
    "feedqube": {
      "type": "http",
      "url": "https://app.feedqube.com/api/mcp",
      "headers": { "Authorization": "Bearer ${input:feedqube-key}" }
    }
  }
}

Getting a key

Create an API key in Feedqube under Settings → AI apps → API keys. Copy it when it is shown: for your security it is shown only once. Treat it like a password and never commit it to a shared repository.

What stays safe

Posts created by an AI app are always saved as drafts. Nothing is published until you approve it in Feedqube, and you can disconnect the app at any time in Settings → AI apps.

If something doesn't work

• Feedqube's tools don't show up: turn Feedqube on in the chat's tools or connectors menu, then start a new chat.
• The sign-in window doesn't open: allow pop-ups for the AI app, or try its web version.
• It can't connect: check that the address is exactly https://app.feedqube.com/api/mcp, and that your Feedqube trial or plan is active.
• It can read but not create drafts: the app (or the API key) is set to read-only. Change it in Feedqube under Settings → AI apps.
• An API key is rejected: it may have been deleted or copied with a space. Create a new one in Settings → AI apps → API keys.