Back
Marketplace/Keboola

TL;DR

Keboola is a Data Engineering MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent build data workflows, integrations, and analytics on a single platform. Install in 1 minute with mcpizy install keboola.

🔄

Keboola

Verified

Data Engineering

Last updated May 30, 2026 · By MCPizy team

Build data workflows, integrations, and analytics on a single platform. ETL and data orchestration.

Install Keboola

Via MCPizy CLI (recommended):
mcpizy install keboola
Or run directly:
npx -y @keboola/mcp-server
View on GitHub

Works with

Claude Code
Claude Desktop
Cursor
Windsurf
VS Code + Copilot
Any MCP Client

More Data Engineering MCPs

🌀

Apache Airflow

Trigger DAGs, inspect task runs, and manage Airflow workflows from any MCP client.

🌊

Apache Kafka

Produce and consume Kafka messages, inspect topics and consumer groups from AI agents.

Alternatives to Keboola

If Keboola doesn't fit your stack, these Data Engineering MCP servers solve similar problems.

⛏️

Powerdrill

Smart data analysis and visualization. Natural language queries over your datasets.

🗂️

Atlan

Metadata capabilities from Atlan for data governance and cataloging.

📐

Reexpress

Statistical verification for search and data science workflows.

Key Takeaways

  • Keboola exposes an MCP interface for data engineering workflows in Claude Code, Cursor and Windsurf.
  • No authentication required — works out of the box once installed.
  • Install in 1 command: mcpizy install keboola — config written to your client automatically.
  • Free and open source (GitHub source linked above) — verified compatible with every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + Copilot).
  • Best use case: automate data engineering workflows from your AI agent without leaving the editor.

Frequently asked questions

What is the Keboola MCP server?

The Keboola MCP server is an Data Engineering Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents build data workflows, integrations, and analytics on a single platform. It exposes Keboola's capabilities as tools the AI can call directly from your editor or CLI.

How do I install Keboola MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install keboola` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @keboola/mcp-server` and restarting Claude Code.

Is Keboola MCP free?

Yes. The Keboola MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Keboola account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.

Does Keboola MCP work with Cursor and Windsurf?

Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.

Manage all your MCPs in one place

Monitor usage, track costs, and discover new MCPs.

Get Started Free
What can I do with Keboola MCP?

Once installed, your AI agent can build data workflows, integrations, and analytics on a single platform directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Keboola operations, inspect results, chain Keboola with other MCP servers (see our Workflow Recipes), and automate repetitive data engineering tasks without leaving your editor.