//n8n AI Automation Index
How do AI agents (Claude Code, Cursor) build n8n workflows through MCP: build or maintain?
Maintain. Of 1,870,624 tool calls last week, 57% read workflows, executions and lists, and 15% write. Fetching executions alone is 28% of calls. In the same week 98,122 workflows were created, 14,017 a day.
- Last updated
- Sep 10, 2026
- Data window
- Aug 25–31, 2026
- Author
- Romuald Członkowski
- Tue 2521,253
- Wed 2619,521
- Thu 2720,651
- Fri 2815,474
- Sat 297,999
- Sun 308,033
- Mon 315,191
Agents check what happened after a run before fixing the workflow. Each create is followed by 9 updates. Only 10% of active installs created a workflow during the week, and 448 installs (3.7% of creators) built 31 or more each.
43% of n8n API connection checks fail, and 76% of those failures are a wrong address or unreachable network. That is the first thing to check when putting AI on an existing instance.
History
One row per weekly issue. The table grows with every update.
| week | workflows | calls | reads | writes | week-1 retention |
|---|---|---|---|---|---|
| 2026-W35 | 98,122 | 1,870,624 | 57% | 15% | 69% |
Methodology · Data and charts may be reused with attribution (CC BY 4.0).