Keboola MCP Server
by Keboola
The Keboola MCP Server is a Model Context Protocol server designed for interacting with Keboola Connection. It provides tools for listing and accessing data from the Keboola Storage API.
Last updated: N/A
What is Keboola MCP Server?
The Keboola MCP Server is a tool that enables interaction with Keboola Connection's Storage API using the Model Context Protocol. It allows users to list, access, and export data from Keboola Storage.
How to use Keboola MCP Server?
The server can be installed manually or via Smithery. It requires Python 3.10+, a Keboola Storage API token, and a Snowflake or BigQuery Read Only Workspace. Configuration instructions are provided for Claude Desktop and Cursor AI, involving setting environment variables and specifying command-line arguments.
Key features of Keboola MCP Server
Lists buckets and tables in Keboola Storage
Provides bucket and table information
Previews table data
Exports table data to CSV format
Lists components and configurations within Keboola Connection
Use cases of Keboola MCP Server
Integrating Keboola data with Claude Desktop for enhanced data analysis
Using Keboola data within Cursor AI for AI-powered code generation and data exploration
Accessing and manipulating Keboola data programmatically
Building custom data applications on top of Keboola Connection
FAQ from Keboola MCP Server
What are the requirements for running the Keboola MCP Server?
What are the requirements for running the Keboola MCP Server?
Python 3.10 or newer, Keboola Storage API token, and a Snowflake or BigQuery Read Only Workspace.
How do I install the server?
How do I install the server?
You can install it manually by cloning the repository and installing dependencies, or automatically via Smithery.
How do I configure the server for Claude Desktop?
How do I configure the server for Claude Desktop?
You need to create or edit the Claude Desktop configuration file and add the server configuration with the correct paths, API URL, and environment variables.
How do I configure the server for Cursor AI?
How do I configure the server for Cursor AI?
You can configure it using Server-Sent Events (SSE) or Standard I/O (stdio) by editing the Cursor AI configuration file and providing the necessary connection details.
What should I do if I encounter connection issues?
What should I do if I encounter connection issues?
Check the logs in Claude Desktop or Cursor AI for error messages, verify your Keboola Storage API token, ensure all paths are absolute, and confirm the virtual environment is properly activated.