Cursor is a code editor with a built-in AI assistant that supports the Model Context Protocol. For advertising engineers and technical marketers, connecting Cursor to your ad accounts means you can query live campaign data while writing the code that interacts with it — no context switching, no stale exports. Ask Cursor 'What are the current search terms wasting budget?' while writing a script to automate negative keyword additions, and the AI answers from your actual account rather than from hypothetical data.
The primary use case for Cursor plus Digital Face is building automation: reporting scripts, budget pacing monitors, campaign health dashboards, and custom alert systems. Having live account data available in the editor means the scripts you write are grounded in real account structure and real performance data from the start.
This setup requires Cursor version 0.40 or later (which ships with MCP support) and a Digital Face account with at least one ad platform connected. The setup takes about 10 minutes.
Step one: sign up at digital-face.nl/signup and connect your Google Ads or Meta Ads account via OAuth. Once connected, go to Settings → MCP Configuration and copy the server configuration block. The Digital Face MCP server URL is https://digital-face.nl/api/mcp.
Step two: open Cursor and go to Settings (Cmd+, on macOS). In the Settings search bar, type MCP. You will see an MCP Servers section. Click Add MCP Server.
Step three: fill in the server details. Name: Digital Face. Transport: HTTP. URL: https://digital-face.nl/api/mcp. Headers: add Authorization with the value Bearer YOUR_TOKEN, where YOUR_TOKEN is the token from your Digital Face dashboard. Save the configuration.
Step four: test the connection. Open a new Cursor Composer session (Cmd+I) and ask: 'What campaigns are currently running in my Google Ads account?' Cursor will call the Digital Face MCP server and return a live summary. If you see an error, verify the Authorization header is formatted as 'Bearer ' followed by your token with no extra whitespace.
With the connection active, the most useful development workflows are: writing a script and asking Cursor to pull the actual account structure it should operate on ('show me all campaigns in paused state with spend over $500 last month'), debugging automation by querying what actually changed ('list the negative keywords added to Campaign X in the last 7 days'), and building reports that reference real metric ranges from the account. Live data context makes Cursor's code suggestions more accurate for ad-specific work because it operates on real account shapes, not imagined ones. Free plan at digital-face.nl.