How we connected Notion AI to 160 new apps in three weeks

Summary

Notion used the Model Context Protocol (MCP), an open standard for connecting AI tools to other apps, to expand its AI integrations. Previously, each new MCP connection required hours of manual setup, including creating accounts, navigating developer settings, and testing, so only 25 apps were connected. In three weeks, Notion grew that number to 185 by building a Notion agent that automates the pipeline from setup to production. The agent handles sign-ups, browser clicks, and tests, while humans still review code changes, design assets, and partner with vendors. A key lesson was that private developer apps could pass internal tests but fail for customers, so the agent now tests from a second account simulating real users.

Takeaways

1. 1

   Building an internal agent to automate account creation, CAPTCHAs, and browser-based setup can slash MCP integration time from hours to minutes.

2. 2

   Private developer apps can cause MCP connections to pass internal tests but fail for customers; simulating real-user credentials in a second test account catches this.

3. 3

   Splitting an agent runbook into one page per pipeline step prevents it from skipping steps due to excessive context in a single instruction.

FAQ