Model Context Protocol

Point your assistant
at your warehouse.

Dataki runs a remote MCP server. Claude, Cursor, ChatGPT and VS Code connect to one URL and can query the sources you have already connected — writing the SQL, saving dashboards and publishing embeds under your own key, and never seeing a database credential.

endpoint streamable http
https://dataki.ai/api/mcp

Nothing to install · your key's scopes, team restriction and spend ceiling all still apply · every query logged.

01 Connecting

One URL. Sign in, or paste a key.

Create an API key in Dataki, then paste one of these into your client's MCP config. The key is the whole auth story: the server holds no credential of its own and acts only as you, so anything your key cannot reach, it cannot reach either.

Create an API key
Claude · Cursor mcp.json 
{
  "mcpServers": {
    "dataki": {
      "type": "http",
      "url": "https://dataki.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_DATAKI_API_KEY"
      }
    }
  }
}
VS Code .vscode/mcp.json 
{
  "servers": {
    "dataki": {
      "type": "http",
      "url": "https://dataki.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer ${input:dataki_key}"
      }
    }
  }
}

Or don't paste anything. ChatGPT and claude.ai take the endpoint on its own and negotiate the rest: the server runs an OAuth 2.1 authorization server with PKCE and dynamic client registration, so a client discovers where to send you, you sign in and approve the scopes, and it gets its own revocable credential. No key ever passes through a config file.

02 Tools

Twelve tools, in the order you would use them.

An assistant finds the sources, reads what the columns actually mean, then queries. The rest exist because an answer nobody keeps is a message that scrolls away.

  • list_sources List data sources

    Start here — the ids every other tool expects.

  • get_data_context Read what this data means

    Metric definitions, join paths, column warnings.

  • record_data_context Write back what it learned

    So the next session starts where this one ended.

  • query Run a query

    SQL against one or more sources, inside your spend boundary.

  • save_dashboard Save a dashboard

    Turn an answer into something that persists.

  • save_widget Save a widget

    Add one chart to a board that already exists.

  • update_dashboard Update a dashboard

    Change what is on a board.

  • get_dashboard Read a dashboard

    What is on a board right now.

  • schedule_refresh Schedule a refresh

    Keep a board current without being asked.

  • watch_metric Watch a metric

    Get told when a number moves.

  • list_schedules List schedules

    What is already running.

  • publish_embed Publish an embed

    A public link, or a signed one for your own product.

03 Verifying

Check it from a terminal first.

Before wiring it into an assistant, list the tools yourself. A valid key returns the twelve above; no key returns a 401 that tells your client where to authenticate rather than just refusing it.

More on the assistant
tools/list shell 
curl -sX POST https://dataki.ai/api/mcp \
  -H "Authorization: Bearer YOUR_DATAKI_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
what the agent then sends query 
SELECT plan, SUM(mrr) AS mrr
FROM   billing.subscriptions
WHERE  status = 'active'
GROUP BY plan
ORDER BY mrr DESC

Free while we are in beta.

Connect a source, create a key, and point your assistant at it.

Start building for free See it in action