FeedbackJar
MCP Integration ✓ 2 minutes setup

FeedbackJar + GitHub Copilot

.vscode/mcp.json (workspace) or user MCP config

GitHub Copilot in VS Code uses a different config format than Cursor — the top-level key is servers, not mcpServers. Add FeedbackJar to .vscode/mcp.json and Copilot agent mode can read and act on user feedback.

How to connect FeedbackJar to GitHub Copilot

1

Create an API token

bash
# Workspace token: Dashboard → Settings → API Tokens
# Copy your fj_live_... token
2

Create .vscode/mcp.json

json
{
  "servers": {
    "feedbackjar": {
      "type": "http",
      "url": "https://api.feedbackjar.com/mcp",
      "headers": {
        "Authorization": "Bearer fj_live_..."
      }
    }
  }
}

VS Code uses "servers" — not "mcpServers". This is the main difference from Cursor and Claude Code.

3

Start the MCP server

bash
# Open .vscode/mcp.json in VS Code
# Click "Start" at the top of the file

# Or use Command Palette:
# MCP: List Servers → feedbackjar → Start

Copilot discovers tools after the server starts. You may need to approve the server on first connect.

4

Use in Copilot Chat

bash
# In Copilot Chat (Agent mode), try:
@feedbackjar list the top open bugs

# Or:
Search FeedbackJar for posts mentioning "login"

What you get

  • Workspace .vscode/mcp.json — share with your team
  • HTTP remote server support
  • Works in Copilot Chat agent mode
  • IntelliSense for config schema
  • User-level config also supported
  • Start/stop servers from the editor

Close the loop from GitHub Copilot

Users report bugs through your widget. Your agent reads the top votes via MCP, ships the fix, and every voter gets notified.

Start Free Trial 7-day free trial · No credit card required

Frequently Asked Questions

Looking for the full tool reference? Read the MCP Server docs →