Build, run, and debug CloverDX jobs from the AI development tools your team already uses.
CloverDX Server exposes an MCP API with more than 50 tools covering graph editing, job execution, validation, edge-level debug data, run tracking, server diagnostics, and other development and operational tasks. The MCP Server also provides access to CloverDX reference knowledge, so connected AI clients can work with current product information instead of relying only on what the underlying model learned during training.
What to expect from this session:
In this session, we’ll connect an external AI development tool to CloverDX Server and work through a complete task: assign the work, review the generated graph, execute it, inspect the results, and examine the data that flowed through individual edges. We’ll also cover setup, permission scoping, and the practical differences between using the AI Assistant in Designer and using CloverDX through an external AI client such as Claude Code or Cursor.
Why you should join:
If your engineering team already works in Claude Code, Cursor, or another MCP-compatible client, this session shows how CloverDX can fit into that workflow. An AI Authoring seat supports both the Designer Assistant and MCP-based authoring from an external client. Read-only server diagnostics through MCP are available without an AI Authoring seat, which also gives operations teams a way to start using the integration for troubleshooting and inspection.
Petr Drabek has spent over 14 years with CloverDX, championing customer success and helping customers maximize value from their data integration initiatives.
Pavel Najvar has worked with CloverDX for more than 16 years, engaging in various roles combining R&D, product development, solutions and marketing.
