- AUTOMATED
- REPORTED
- HUMAN
- AUDITED
Short answer
How can I use AI to check my data pipelines?
Your AI triggers specific Metaplane monitors and pulls their current status to confirm your data is still valid. This lets you verify integrity immediately after a schema change or a new deployment. You'll see exactly which monitors passed or failed.
The results.
Where your data checks land.
The AI handles the execution and status retrieval, leaving you to handle the fixes.
AUTOMATED
Immediate validation
The AI runs the monitors you specify. You get a clean pass or fail signal without manual clicking.
REPORTED
Status summaries
Your agent pulls the latest results from Metaplane. It presents the health of your pipelines in your chat window.
HUMAN
Manual remediation
If a monitor fails, the AI identifies the issue. You decide how to fix the underlying data or code.
AUDITED
Deployment logs
The AI can list all existing monitors to ensure your new deployment is covered by the right checks.
The workflow
What your AI does when <the thing arrives>.
The AI acts as your bridge to Metaplane, turning your natural language requests into active data tests.
Identify monitors
The AI looks through your Metaplane setup to find the specific monitors relevant to your current task.
list_monitorsStart the check
Once you pick a monitor, the AI tells Metaplane to run it immediately.
trigger_monitor_runFetch results
The AI waits for the run to finish and then pulls the specific details of that monitor's performance.
get_monitorReport health
The AI summarizes whether the data passed or failed based on the retrieved status.
get_monitor
Try it
Copy these to start.
Use these prompts to kick off your first data validation task.
Starting points
Swap the bracketed text for your actual monitor names or specific pipeline identifiers.
Metaplane Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_ZzPtEvduP33DM4pFjpxFzBv2qdMoX1IaKAzD75wY/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Metaplane capabilities are ready to use.
{
"mcpServers": {
"metaplane-mcp": {
"url": "https://edge.vinkius.com/vk_preview_ZzPtEvduP33DM4pFjpxFzBv2qdMoX1IaKAzD75wY/mcp"
}
}
}Run the 'Sales_Data_Integrity' monitor in Metaplane now.
List all my Metaplane monitors so I can see what's active.
Check the status of the 'Schema_Change_Check' monitor.
After I deploy this change, trigger a run for all monitors in the 'Production' group.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Metaplane once, then ask.
Just link your Metaplane account to Vinkius. Your credentials stay encrypted, and you can immediately start asking your AI to run checks.
Connect Metaplane to your AIFAQ
How this task behaves.
- 01
Can the AI fix a broken data pipeline?
No. The AI can trigger the check and tell you it failed, but you must manually fix the data or the code.
- 02
Can the AI create new monitors in Metaplane?
No. The AI can only list, trigger, or get status for monitors that already exist in your account.
- 03
Does the AI run monitors on a schedule?
No. The AI only triggers on-demand runs when you specifically ask it to.
- 04
Can I see the results of a monitor run in my chat?
Yes. The AI pulls the status and details from Metaplane and presents them to you directly.
- 05
Will the AI delete any of my Metaplane configurations?
No. The AI only has permission to read and trigger existing monitors.
More questions about Metaplane? The Connector page answers them. See everything the Metaplane Connector can do
Connect Metaplane to Claude, Cursor, ChatGPT & more
