AIbase
EN
Explore
Keboola Explorer
K

Keboola Explorer

The Keboola MCP Server is a Model Context Protocol server for interacting with Keboola Connection, providing tools to access Keboola storage API data and supporting use on platforms such as Claude Desktop and Cursor AI.
Cloud platformDeveloper tools#Data storage#SQL query#Keboola tools#AI integration.Python
2.5 points
24

What is the Keboola MCP Server?

The Keboola MCP Server is a middleware service that allows you to directly interact with the Keboola Connection platform through AI assistants (such as Claude or Cursor). It offers various functions such as querying data, managing buckets and tables, and running transformations without directly using the Keboola interface or API.

How to use the Keboola MCP Server?

You can connect to the MCP server by configuring an AI client (such as Claude Desktop or Cursor AI). After the server is running, you can directly interact with Keboola data using natural - language commands in the chat interface.

Use cases

It is suitable for data analysts, business intelligence users, and developers, especially those who want to quickly query Keboola data using natural language without writing complex SQL or using the full interface.

Main features

Storage toolsBrowse and manage buckets and tables in Keboola storage, including viewing detailed information and updating descriptions.
SQL toolsExecute SQL queries directly in the Keboola workspace, supporting Snowflake and BigQuery.
Component toolsManage and create component configurations, including SQL transformations.
Job toolsView and manage Keboola jobs, including starting new jobs.

Advantages and limitations

Advantages
Simplify Keboola data access through a natural - language interface.
Support multiple AI clients (Claude, Cursor, etc.).
Provide comprehensive coverage of Keboola functions.
Support two backends, Snowflake and BigQuery.
Limitations
Require configuration of the Keboola API token and workspace.
BigQuery requires additional Google Cloud credentials.
Some advanced functions may require direct use of the Keboola interface.

How to use

Install the server
Install the keboola_mcp_server package via pip or use Smithery for automatic installation.
Configure the AI client
Edit the configuration file according to the AI client you are using (Claude or Cursor).
Set environment variables
Configure the Keboola storage API token and workspace information.
Start the server
Run the server and connect to the AI client.

Usage examples

Data explorationQuickly browse the data structure and content in the Keboola project.
Data queryQuery data in a specific table directly from the chat interface.
Transformation managementCreate and manage data transformations.

Frequently Asked Questions

How to obtain the Keboola storage API token?
Why does BigQuery require additional configuration?
Which AI clients does the server support?
How to update the description of a bucket or table?

Related resources

GitHub repository
Project source code and issue tracking.
Keboola documentation
Official documentation for Keboola Connection.
MCP protocol specification
Technical specification for the Model Context Protocol.
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "keboola": {
      "command": "uvx",
      "args": [
        "keboola_mcp_server",
        "--api-url",
        "https://connection.YOUR_REGION.keboola.com"
      ],
      "env": {
        "KBC_STORAGE_TOKEN": "your-keboola-storage-token",
        "KBC_WORKSPACE_SCHEMA": "your-workspace-schema"
      }
    }
  }
}

{
  "mcpServers": {
    "keboola": {
      "url": "http://localhost:8000/sse?storage_token=YOUR-KEBOOLA-STORAGE-TOKEN&workspace_schema=YOUR-WORKSPACE-SCHEMA"
    }
  }
}

{
  "mcpServers": {
    "keboola": {
      "command": "uvx",
      "args": [
        "keboola_mcp_server",
        "--transport",
        "stdio",
         "--api-url",
         "https://connection.YOUR_REGION.keboola.com"
      ],
      "env": {
        "KBC_STORAGE_TOKEN": "your-keboola-storage-token", 
        "KBC_WORKSPACE_SCHEMA": "your-workspace-schema"         
      }
    }
  }
}

{
  "mcpServers": {
    "keboola": {
      "command": "wsl.exe",
      "args": [
        "bash",
        "-c",
        "'source /wsl_path/to/keboola-mcp-server/.env",
        "&&",
        "/wsl_path/to/keboola-mcp-server/.venv/bin/python -m keboola_mcp_server.cli --transport stdio'"
      ]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
348
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
838
4.3 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
333
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
116
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
624
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
562
5 points
C
Cloudflare
Changesets is a build tool for managing versions and releases in multi - package or single - package repositories.
TypeScript
1.5K
5 points
K
Kubernetes
An MCP server based on Kubernetes for managing and operating Kubernetes clusters
TypeScript
553
5 points
Featured MCP Services
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
97
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
150
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
838
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
573
5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
761
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase