- LIVE
- VERIFIED
- LISTED
- HUMAN
Short answer
How do I add new data sources to my AI?
Tell your AI client to create a new connection using the CData Connect Cloud MCP. It will set up the proxy, test the link, and add it to its available data sources. You'll see the results of the connection immediately.
The connection outcomes.
Where your data lands.
What happens once the AI finishes the setup process.
LIVE
Active data access
The AI establishes a bridge to your external database. You can now ask questions about that specific data right away.
VERIFIED
Stable connections
The agent runs a test to confirm the credentials and network path are valid. This ensures queries don't fail later.
LISTED
Updated source list
The new proxy appears in the agent's inventory. It now knows which new tables or schemas are available to read.
HUMAN
Manual fixes
If a connection fails the test, you'll need to step in. You must provide the correct connection strings to fix the error.
The workflow
What your AI does when you request a new connection.
The AI handles the configuration and verification of the data proxy.
Build the proxy
The agent uses your provided credentials to build a new connection profile in the cloud.
cdata_create_connectionTest the link
The AI runs a test to make sure the data source is reachable and permissions are correct.
cdata_test_connectionCheck the list
The agent looks at the current active connections to confirm the new one is registered.
cdata_list_connectionsVerify readiness
The AI checks the updated connection list to ensure the proxy is ready for use.
cdata_list_connections
Try it
Copy these to start.
Use these prompts to trigger the connection process.
Starting points
Swap the bracketed info with your actual database details like host, port, or API keys.
CData Connect Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_SBYp4YpOhOkod1f5osCBPGeYZMDXyp0rzOXZLCrf/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 — CData Connect capabilities are ready to use.
{
"mcpServers": {
"cdata-connect-cloud-mcp": {
"url": "https://edge.vinkius.com/vk_preview_SBYp4YpOhOkod1f5osCBPGeYZMDXyp0rzOXZLCrf/mcp"
}
}
}Create a new connection to my Snowflake instance using these credentials: [insert credentials].
Test the connection I just created to my PostgreSQL database to make sure it works.
Show me a list of all my current data connections so I can see what's active.
Set up a new data proxy for my Salesforce account and verify it is ready to use.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect CData Connect Cloud once, then ask.
Click the button to link the MCP to your client. Your credentials stay encrypted on our side.
Connect CData Connect Cloud to your AIFAQ
How the connection process behaves.
- 01
Can the AI delete my existing database connections?
No. The current tools only allow for creating, testing, and listing connections. It cannot delete or modify existing ones.
- 02
Does the AI need my database password?
You provide the connection details in the chat prompt, which the AI uses to execute the creation tool.
- 03
Can the AI change my database schema?
No. This MCP is for establishing data proxies, not for performing schema modification commands.
- 04
How do I know if the connection actually worked?
The AI will use the test tool and report back whether the handshake was successful or if it hit an error.
- 05
Can I use this to connect to a local file on my desktop?
No. This connector is designed for cloud-based data proxies via CData Connect Cloud.
More questions about CData Connect Cloud? See everything the CData Connect Cloud Connector can do
Connect CData Connect to Claude, Cursor, ChatGPT & more
