- SETUP
- CONTROL
- AUDIT
- HUMAN
Short answer
Can I manage Stitch Data with my AI?
Yes. You can use your AI to set up sources, manage destinations, and trigger syncs manually. This gives you direct control over your data pipelines via your agent.
Pipeline outcomes
What you can accomplish.
Your AI handles the technical configuration of your data flows.
SETUP
New pipelines
The AI uses create_source and create_destination to build your data connections. You just describe what you need.
CONTROL
Manual syncs
You can trigger a data refresh at any time. The AI uses start_sync to run a job immediately.
AUDIT
Inventory check
Ask your agent to list_sources or list_destinations to see your current setup. You get a clear view of your active pipelines.
HUMAN
Safe deletions
The AI won't delete your work without a direct order. You retain control over delete_source and delete_destination commands.
The workflow
What your AI does when the command arrives.
Your agent translates your plain English instructions into Stitch Data actions.
Discovery
The AI checks your existing connections to understand your current data architecture.
list_sourceslist_destinationsProvisioning
When you need new data flows, the AI builds the source and destination connections for you.
create_sourcecreate_destinationMaintenance
The AI modifies existing configurations or stream settings when your requirements change.
update_sourceupdate_destinationupdate_stream_metadataExecution
Once the setup is correct, the AI initiates the data movement.
start_sync
Try it
Copy these to start.
Use these prompts to begin managing your pipelines.
Starting points
These are opening lines. Replace the specific app or database names with your own.
Stitch Data Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_mABPCZrnZTeawQZOSWTl9iyadYUD2LtJD9LLWWGw/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 — Stitch Data capabilities are ready to use.
{
"mcpServers": {
"stitch-data-mcp": {
"url": "https://edge.vinkius.com/vk_preview_mABPCZrnZTeawQZOSWTl9iyadYUD2LtJD9LLWWGw/mcp"
}
}
}List all my current Stitch Data sources.
Create a new MySQL source for my production database.
Start a sync for my Snowflake destination.
Update the metadata for the Zendesk stream.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Stitch Data once, then ask.
Link your account once and your credentials stay encrypted. You can find the full setup guide on the Connector page.
Connect Stitch Data to your AIFAQ
How this task behaves.
- 01
Can the AI delete my sources automatically?
No. The AI only uses delete_source if you explicitly tell it to delete a specific source.
- 02
Can I use this to transform data?
No. This connector manages the movement and configuration of data, not the transformation logic within the pipeline.
- 03
Can I trigger a sync via chat?
Yes. You can tell your agent to start a sync for a specific destination or source.
- 04
Will the AI change my destination without permission?
No. The AI only uses update_destination when you give it a direct instruction to change a destination's settings.
- 05
Can I see what sources are connected?
Yes. You can ask your AI to list all your active sources at any time.
More questions about Stitch Data? See everything the Stitch Data Connector can do
Connect Stitch Data to Claude, Cursor, ChatGPT & more
