Keboola
This server facilitates interaction with Keboola's Storage API, enabling users to browse and manage project buckets, tables, and components efficiently through Claude Desktop.
What is Keboola?
Keboola is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this server facilitates interaction with keboola's storage api, enabling users to browse and manage project buckets, tables, and components efficiently through claude desktop.
This server facilitates interaction with Keboola's Storage API, enabling users to browse and manage project buckets, tables, and components efficiently through Claude Desktop.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This server facilitates interaction with Keboola's Storage A
Use Cases
Maintainer
Works with
Installation
NPM
npx -y keboola-mcp-serverPIP
pip install keboola-mcp-serverManual Installation
npx -y keboola-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Keboola
The Keboola MCP Server connects Claude and other MCP-compatible clients directly to the Keboola Data Platform, giving AI assistants the ability to browse storage buckets and tables, run SQL transformations, orchestrate ETL jobs, and manage data pipelines through natural language. It is the official integration maintained by Keboola, making it a reliable choice for data engineers and analysts who want to query and manage their Keboola projects without leaving their AI assistant.
Prerequisites
- A Keboola account with at least one active project
- A Keboola Storage API token (master or custom) — generated in Project Settings > API Tokens
- The Keboola Storage API URL for your region (e.g. https://connection.keboola.com for US, https://connection.eu-central-1.keboola.com for EU)
- Python 3.10+ or Node.js 18+ depending on your chosen install method
- An MCP-compatible client such as Claude Desktop or Claude Code
Generate a Keboola Storage API token
Log in to your Keboola project, navigate to Settings > API Tokens, and create a new token. Copy the token value — it will only be shown once. For read-only access use a limited-scope token; for full pipeline management use a master token.
Install the server package
Install the keboola-mcp-server Python package into your environment, or use npx to run it directly without a global install.
pip install keboola-mcp-serverConfigure your MCP client
Add the Keboola server entry to your Claude Desktop config, setting KBC_STORAGE_TOKEN and KBC_STORAGE_API_URL. Replace the token and URL with values from your project.
{
"mcpServers": {
"keboola": {
"command": "npx",
"args": ["-y", "keboola-mcp-server"],
"env": {
"KBC_STORAGE_TOKEN": "your-keboola-storage-token",
"KBC_STORAGE_API_URL": "https://connection.keboola.com"
}
}
}
}Alternatively, use the hosted HTTP transport
Keboola provides a fully-managed MCP endpoint per region. With Claude Code you can add it in one command, avoiding any local installation.
claude mcp add --transport http keboola https://mcp.keboola.com/mcpRestart your client and verify the connection
Quit and reopen Claude Desktop (or reload Claude Code). Ask a simple question about your project to confirm the server is connected and the token is valid.
Keboola Examples
Client configuration
Claude Desktop configuration using the local npx install with environment variable authentication.
{
"mcpServers": {
"keboola": {
"command": "npx",
"args": ["-y", "keboola-mcp-server"],
"env": {
"KBC_STORAGE_TOKEN": "your-keboola-storage-token",
"KBC_STORAGE_API_URL": "https://connection.keboola.com",
"KBC_WORKSPACE_SCHEMA": "optional-workspace-schema"
}
}
}
}Prompts to try
Natural language prompts that exercise the server's storage, SQL, and pipeline capabilities.
- "What buckets and tables exist in my Keboola project?"
- "Run a query to show the top 10 customers by total order value from the orders table."
- "Create a SQL transformation that joins the customers and orders tables on customer_id."
- "What components and transformations are configured in this project?"
- "Show me the latest job execution status for all transformations."Troubleshooting Keboola
Authentication fails with 'Invalid token' error
Confirm that KBC_STORAGE_TOKEN matches the token shown in Keboola Project Settings > API Tokens and that KBC_STORAGE_API_URL points to the correct region endpoint. US projects use https://connection.keboola.com while EU projects use https://connection.eu-central-1.keboola.com.
Custom token cannot query certain tables
Custom tokens require KBC_WORKSPACE_SCHEMA to be set. Go to Project Settings, create a workspace, and set its schema name as the KBC_WORKSPACE_SCHEMA env var. Master tokens do not have this requirement.
Server connects but returns no data
Check that the project referenced by your token has at least one bucket with tables. Also verify that your token has read access to the relevant buckets under API Token permissions.
Frequently Asked Questions about Keboola
What is Keboola?
Keboola is a Model Context Protocol (MCP) server that this server facilitates interaction with keboola's storage api, enabling users to browse and manage project buckets, tables, and components efficiently through claude desktop. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Keboola?
Install via npm with the command: npx -y keboola-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Keboola?
Keboola works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Keboola free to use?
Yes, Keboola is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Keboola Alternatives — Similar Cloud Services Servers
Looking for alternatives to Keboola? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Keboola in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Keboola?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.