//n8n AI Automation Index
How do AI agents (Claude Code, Cursor) build n8n workflows through MCP: build or maintain?
Maintain. Of 2,502,508 tool calls last week, 60% read workflows, executions and lists, and 14% write. Fetching executions alone is 32% of calls. In the same week 118,918 workflows were created, 16,988 a day.
- Last updated
- Sep 25, 2026
- Data window
- Sep 7–13, 2026
- Author
- Romuald Członkowski
- Mon 718,361
- Tue 819,957
- Wed 920,090
- Thu 1020,223
- Fri 1118,305
- Sat 1211,104
- Sun 1310,878
Agents check what happened after a run before fixing the workflow. Each create is followed by 8 updates. Only 10% of active installs created a workflow during the week, and 506 installs (3.2% of creators) built 31 or more each.
12% of n8n API connection checks fail, and 63% 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-W37 | 118,918 | 2,502,508 | 60% | 14% | 57% |
| 2026-W36 | 98,043 | 1,784,850 | 60% | 15% | n/a |
| 2026-W35 | 98,122 | 1,870,624 | 57% | 15% | n/a |
Methodology · Data and charts may be reused with attribution (CC BY 4.0).