Press CTRL+K to open search

Claude

  • 8 minute(s) read
Prev Next

Claude is Anthropic's AI assistant. This destination lets Claude read data from any source you connect in Dataddo, so you can ask questions about your data in plain language. Dataddo delivers the data directly to the model and takes care of the rest.

Dataddo handles the whole pipeline for you. It keeps the data fresh, stores it in SmartCache, and serves it through a built-in querying layer. Every answer comes with metadata: technical metadata such as data freshness, and business metadata such as what each table and column means. You do not write any code.

How It Works

On the Data Anywhere and Enterprise plans, Claude is a destination, and the data comes from the flows you attach to it. On the Data to AI plan, Claude is an AI Model, and the data comes from the Contexts you attach to it. A Context is data that Dataddo keeps ready to query. When Claude needs data, Dataddo serves it from SmartCache and returns the rows together with their freshness and business metadata.

Access is authorized with OAuth. You sign in to Dataddo from Claude once, with your Dataddo email and password. The sign-in page does not offer Google or Microsoft single sign-on. Claude then keeps the connection active and renews it in the background, so you do not handle any tokens.

What Claude Can Do with Your Data

Dataddo exposes your data through its data MCP server at https://headless.dataddo.com/mcp-data. The server is a semantic layer: Claude asks in business terms (customers, invoices, deals), and Dataddo never accepts SQL from the model. The tools fall into these groups:

Tools Purpose
list_flows, describe_flow See which flows are available to your account and what each one holds.
list_models, list_entities, describe_entity, search, sample_values Find the business entities, fields, relationships and metrics that can be queried.
query Query an entity by field names, with filters, grouping, date grains and predefined metrics.
data_status, known_gaps Check how fresh the data is and which questions the data cannot answer.
refresh, report_problem Check whether fresher data is available for an entity (this does not start a new extraction), or record an answer that looks wrong.

A flow or Context can be available but not yet queryable. The model can see it as soon as it is attached, but it can query it only after a semantic model covers it. list_flows reports this for each one.

Setup Overview

The steps depend on your Dataddo plan:

  • On the Data Anywhere and Enterprise plans, you work with sources, flows and destinations.
  • On the Data to AI plan, you work with Contexts and AI Models instead.
  1. Create a Claude authorizer.
  2. Make your data available:
    • Data Anywhere and Enterprise: create a Claude destination that uses the authorizer, then attach one or more flows to it.
    • Data to AI: create a Claude AI Model that uses the authorizer, then attach one or more Contexts to it.
  3. Add the Dataddo Data Access connector from the Claude Connectors directory and sign in with your Dataddo account.

After you sign in, Claude can access every flow or Context attached to an AI destination or AI Model in your Dataddo account, not only the ones attached to Claude. Their data appears after they run for the first time.

Authorize Connection to Claude

Authorize the connection so Dataddo can serve your data to Claude:

  1. Go to Authorizers and click Authorize New Service.
  2. Select Claude.
  3. Fill in the field below and click Save. Dataddo validates the connection when you save it.
Field Description
Label A name for this authorizer in Dataddo.

Make Your Data Available to Claude

Follow the steps for your plan.

Data Anywhere and Enterprise Plans

  1. Go to Destinations, click Create Destination, and select Claude.
  2. Enter a name, choose the authorizer you created, and click Save.
  3. Go to Flows and click Create Flow.
  4. Add one or more sources.
  5. Add the Claude destination.
  6. Set the schedule that keeps the data fresh and click Save.

Data to AI Plan

  1. Go to AI Models and add a new one.
  2. Select Claude.
  3. Enter a name and choose the authorizer you created.
  4. Attach one or more Contexts to the AI Model.
  5. Click Save.

Set Up the Connection in Claude

Dataddo Data Access is listed in the Claude Connectors directory: Dataddo Data Access. You add it from the directory, so you do not need to enter a server URL or configure authentication. The same connector works in the Claude web app, Claude Desktop, the mobile apps and Claude Code.

Claude

Add the Connector

On the Pro and Max plans, you add the connector yourself. On the Team and Enterprise plans, an Owner adds it once for the organization, and each member then connects with their own Dataddo account. On the Enterprise plan, a member whose custom role includes managing the organization's libraries can add it too.

  1. Open the directory:
    • Pro and Max: go to Customize > Connectors and select Discover.
    • Team and Enterprise Owners: go to Organization settings > Connectors and browse the connectors there.
  2. Search for Dataddo Data Access and open its page.
  3. Click Connect to Claude. On the Team and Enterprise plans, an Owner clicks Connect for your team, which adds the connector for the whole organization.

On the Team plan, members who cannot add connectors see Request instead. Clicking it sends a request to the organization's Owners, who can enable the connector in Organization settings > Connectors.

Sign In to Dataddo

  1. Claude opens the Dataddo sign-in page. On the Team and Enterprise plans, each member starts it from Customize > Connectors by selecting Dataddo Data Access and clicking Connect to Claude.
  2. Sign in with your Dataddo email and password, and complete multi-factor authentication if asked.
  3. After you sign in, you return to Claude. The connector is listed under Your connectors with the status Connected.

To control how Claude uses the tools, open the connector in Customize > Connectors and go to Tool permissions. For each tool, choose Always allow, Needs approval or Blocked.

Use It in a Chat

In a chat, select + in the message box, go to Connectors, and turn on Dataddo Data Access. Then ask a question about your data, for example "Which flows do I have in Dataddo?".

Connector Added Before the Directory Listing

If you added Dataddo earlier as a custom connector, it keeps working and appears under Custom in Customize > Connectors. To switch to the directory listing, remove the custom connector and add Dataddo Data Access from the directory. Claude then asks you to sign in to Dataddo again. Do not keep both, or Claude has two Dataddo connections.

Claude Code

If you sign in to Claude Code with your Claude account, connectors added in Claude are available in Claude Code automatically. Add Dataddo Data Access in Claude as described above, then run /mcp in Claude Code and check that the connector is listed as Connected.

Connectors from Claude are not loaded when Claude Code uses an API key or a third-party provider such as Amazon Bedrock. In that case, add the server manually:

  1. Add the server from your terminal:

    claude mcp add --transport http dataddo https://headless.dataddo.com/mcp-data

    The server is added to the current project. To use it in all your projects, add --scope user.

  2. Sign in. Run claude mcp login dataddo, or run /mcp inside Claude Code, select the dataddo server and authenticate. A browser window opens with the Dataddo sign-in page. In an SSH session without a browser, run claude mcp login dataddo --no-browser instead.

  3. Sign in with your Dataddo email and password, and complete multi-factor authentication if asked.

  4. Run /mcp, or claude mcp list from your terminal, and check that the dataddo server shows Connected.

Claude Code stores the credentials in the system keychain on macOS and in a credentials file on other systems, and renews them automatically. To sign out, run claude mcp logout dataddo.

A server added manually in Claude Code takes precedence over the Claude connector with the same URL. /mcp then lists the connector as hidden. Keep only one of them.

Troubleshooting

  • A flow or Context is missing: attach it to an AI destination or AI Model in the Dataddo account you signed in with, then let it run.
  • The connector shows Reconnect or Connect, or Claude Code shows Needs authentication: the sign-in expired or was revoked. Connect again, or select Re-authenticate in /mcp, and sign in to Dataddo.
  • You see Request instead of Connect to Claude on the Team plan: an Owner has not added the connector for the organization yet. Click Request, or ask an Owner to add it.
  • Dataddo appears twice, or under Custom: it was added earlier as a custom connector. Remove the custom one and keep the directory connector.
  • Claude Code does not list the connector: run /status and check that you are signed in with your Claude account, not an API key. Otherwise, add the server manually as described above.
  • A manually added Dataddo server does not open the sign-in page: check that the URL is exactly https://headless.dataddo.com/mcp-data and that you did not add an authorization request header.
  • Claude shows "Authorization with the MCP server failed": try again. If it keeps failing, send the reference that starts with ofid_ from the browser address bar to Dataddo support.
  • You see data from the wrong Dataddo account: you signed in with a different account. Disconnect the connector, then connect it again and sign in with the right account.
  • A flow or Context is listed but Claude cannot query it: it is available but no semantic model covers it yet.
  • Claude cannot fetch data: check that the flow has run at least once, so the Context holds data.
  • Stale data: review the flow schedule. Dataddo serves the most recent data it has stored for the Context.

Related Articles