Press CTRL+K to open search

Grok

  • 5 minute(s) read
Prev Next

Grok is xAI's AI assistant. This destination lets Grok read data from any source you connect in Dataddo, so you can ask questions about your data in plain language. It works in the Grok app (grok.com, iOS and Android) through a custom connector, and in the Grok Build command-line tool. 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, Grok is a destination, and the data comes from the flows you attach to it. On the Data to AI plan, Grok 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 Grok 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 Grok once, with your Dataddo email and password. Grok then keeps the connection active and renews it in the background, so you do not handle any tokens.

What Grok 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: Grok 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 Request fresh data for an entity, or report 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 Grok authorizer.
  2. Make your data available:
    • Data Anywhere and Enterprise: create a Grok destination that uses the authorizer, then attach one or more flows to it.
    • Data to AI: create a Grok AI Model that uses the authorizer, then attach one or more Contexts to it.
  3. Add Dataddo as a custom connector in Grok, or as an MCP server in Grok Build, and sign in with your Dataddo account.

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

Authorize Connection to Grok

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

  1. Go to Authorizers and click Authorize New Service.
  2. Select Grok.
  3. Fill in the fields below and click Save. Dataddo validates the connection when you save it.
Field Description
Label A name for this authorizer in Dataddo.
Dataddo token The Dataddo token used when querying the Dataddo API. If the list is empty, go to Settings > Security > API Tokens and create one.

Make Your Data Available to Grok

Follow the steps for your plan.

Data Anywhere and Enterprise Plans

  1. Go to Destinations, click Create Destination, and select Grok.
  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 Grok 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 Grok.
  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 Grok

You can connect from the Grok app or from Grok Build.

Grok App

Add the Connector

  1. Go to grok.com/connectors.
  2. Click New Connector and select Custom.
  3. Enter the MCP server URL https://headless.dataddo.com/mcp-data. Do not add an API key or headers.
  4. Save the connector. Grok starts the sign-in.

On Grok Business and Enterprise, an admin adds the connector for the team. This needs the Team Read-Write permission. In the admin page, click + Add Connector, select Other and enter the same URL.

Sign In to Dataddo

  1. Grok opens the Dataddo sign-in page.
  2. Enter your Dataddo email and password, and complete multi-factor authentication if you are asked to.
  3. After you sign in, you return to Grok, and the connector shows as connected.

Use It in a Chat

Grok uses the connector's tools on its own when your question is about your data. Ask, for example, "Which flows do I have in Dataddo?".

Grok Build

  1. Add the server from your terminal:

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

  2. Sign in. Grok Build opens the Dataddo sign-in page in your browser the first time it uses the server. You can also press i in the Grok Build interface to sign in to a server right away.

  3. Enter your Dataddo email and password, and complete multi-factor authentication if you are asked to.

  4. Run grok mcp doctor dataddo to check that the server is configured and reachable.

Grok Build stores the credentials in ~/.grok/mcp_credentials.json. To remove the server, run grok mcp remove dataddo.

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.
  • Grok does not open the Dataddo sign-in page: check that the URL is exactly https://headless.dataddo.com/mcp-data and that you did not add an API key or an Authorization header.
  • The connector stops working: the sign-in expired or was revoked. Reconnect the connector in Grok, or run the Grok Build sign-in again, and sign in to Dataddo.
  • You see data from the wrong Dataddo account: you signed in with a different account. Remove the connector, then add it again and sign in with the right account.
  • A flow or Context is listed but Grok cannot query it: it is available but no semantic model covers it yet.
  • Grok 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