Skip to content
[ docs · ai agents ]

Connect your AI agent (MCP)

Dexaflow Cloud documentation · Updated: November 18, 2026

  1. Getting started
  2. Connect your AI agent (MCP)
  3. Plans and limits
  4. Known limitations

Your organization has an MCP server at https://<org>.flow.dexadata.ai/mcp. AI agents connected to it can read your DAGs, runs and logs as you, read-only. Your agent's provider runs the model, so nothing here is billed by Dexaflow.

Claude.ai and ChatGPT

  1. Copy the server URL from AI agents in the console.
  2. Claude.ai: Settings → Connectors → Add custom connector (on Team and Enterprise, an owner adds it). ChatGPT: add it as a custom connector in its connector settings, where your plan allows custom connectors.
  3. Sign in to Dexaflow Cloud and choose Allow. Access is read-only.
  4. To disconnect, remove the connector in the app. Access also ends when you leave the organization.

Claude Code

claude mcp add --transport http dexaflow-<org> https://<org>.flow.dexadata.ai/mcp

Then run /mcp in Claude Code and choose Authenticate.

Cursor, VS Code, CI and headless use

Create a token in AI agents (30 or 90 days) and use the snippet the page shows. The token is shown once; store it as a secret. Revoke it in the same page.

What the agent can do

List DAGs, diagnose failed runs, search logs. It cannot change, run, pause or deploy anything yet.

Try

  • "Which of my pipelines failed in the last 24 hours, and why?"
  • "Diagnose the latest failed run of <a DAG>."
© 2026
Dexaflow documentation GitHub Beta terms Privacy Beta limits

DexaData · CNPJ 28.918.992/0001-50

Apache, Apache Airflow and the Airflow logo are registered trademarks of the Apache Software Foundation. Dexaflow is not affiliated with or endorsed by the ASF.