Connecting Claude to Kaivo
Instructions on how to connect Claude to Kaivo.
Written By Aapo Mannismäki
Last updated 17 days ago
Connect Claude to your Kaivo data warehouse and ask about your business in plain language. You don't need to know your schema or write SQL. Claude finds the right tables itself.
Add the connector
Open claude.ai or Claude Desktop.
Go to Settings → Connectors → Add custom connector. On Team and Enterprise plans an owner does this once, in Admin settings. Everyone else then just clicks Connect.
Paste the Kaivo server address and click Add:
https://mcp.kaivo.io/mcp
Click Connect. Claude sends you to Kaivo to sign in.
Sign in with your Kaivo account and choose which workspace Claude may read.
Back in Claude, turn on the tools you want.
Claude will warn you that the connector isn't verified by Anthropic. That's normal. The warning appears for any connector you add by URL instead of picking one from Anthropic's directory. We're applying for an official listing, which will remove this step.
Everyone connects with their own account
Even when an owner adds the connector for the whole organisation, each person signs in to Kaivo themselves and chooses their own workspace. Your name is what appears on the Members & access page in Kaivo, and each person's access can be withdrawn on its own.
Try it
"What data do we have available?"
"How did sales develop over the last six months?"
"Which customers haven't ordered since spring?"
"Compare campaign spend to revenue by channel last quarter."
"Where does the customer email address live in our warehouse?"
You don't need to name datasets or tables. Claude searches your warehouse to find where the answer lives.
What Claude can and can't do
Claude can browse your datasets and tables, read their schemas and column descriptions, and run queries against your data. It can also save a result as a new table in a scratch dataset called kaivo_ai_outputs, so a BI tool or another pipeline can pick it up later.
Claude cannot change or delete your existing data, and it cannot reach anything outside the workspace you chose. Internal staging tables used by our data pipelines are hidden.
Each query scans at most 1 GB and returns at most 1000 rows. If a result is cut short, Claude will tell you. Narrow the question, or ask for a summary instead of raw rows.
What Claude can see and where your data goes
Claude sees exactly what you see. When you connect, you pick one Kaivo workspace, and Claude can read the datasets in it: the same ones you can already open in Kaivo. It can't reach a workspace you don't have access to, and the internal tables our pipelines use stay hidden. Because access follows your sign-in, even a session that has been fed misleading instructions can only reach what you can reach.
Claude queries your warehouse directly. Kaivo already keeps your data in the warehouse we build and maintain for you. Connecting Claude doesn't add a second copy of it: nothing is exported, indexed, or moved anywhere else to make this work. Queries run in the EU against your live data, and there are no keys for you to look after.
What comes back is the result of your question. Claude writes a query, we run it, and the results go back to Claude, which means they reach Anthropic's servers rather than your own computer. If you ask for a list of customers, that list is what gets sent. Each query returns at most 1000 rows, so it is never a full copy of a table.
You choose the AI tool, so your own agreement with Anthropic is the one that applies. Kaivo never brings in an AI of its own. Whatever your agreement with Anthropic says about training and retention covers the results Claude receives.
Every question leaves an audit trail: who asked, what was queried, and how much data it scanned.
Disconnecting
Removing the connector inside Claude only stops Claude from using it. It does not withdraw access to your data.
To revoke access properly, go to Members & access in Kaivo and click Disconnect next to that tool. Access ends within a few minutes. Disconnecting one tool doesn't affect any others.
Other tools
Claude Code connects from a terminal and can sign in the same way:
claude mcp add --transport http kaivo https://mcp.kaivo.io/mcp
ChatGPT and other AI tools can connect too. See our other setup guides.
Troubleshooting
Claude can't reach the server. Check the address is exactly https://mcp.kaivo.io/mcp, with no trailing slash or spaces.
"Add custom connector" isn't there. On Team and Enterprise plans only an owner can add connectors, from Admin settings. Ask your Claude administrator.
Sign-in works but ChatGPT can't see any data. On a new connection this is usually access still finishing setting up behind the scenes, which takes a few minutes. Wait a moment and ask again. If it's still happening after that, disconnect Kaivo on the Members & access page and connect again. Email us if the problem persists.
The query was too large. It would have scanned more than 1 GB. Add a date filter, or ask for a summary rather than every row.
Claude says a result was truncated. More than 1000 rows matched. Ask for totals, averages or a top 10 instead.
Still stuck? Email support@kaivo.io.