mcp-server

Connect your AI agents, MCP clients (Cursor, Claude, Windsurf, VS Code ...) and other AI assistants to Keboola. Expose data, transformations, SQL queries, and job triggers—no glue code required. Deliver the right data to agents when and where they need it.

Keboola MCP Server is an open-source bridge between your Keboola project and modern AI tools. It turns Keboola features—like storage access, SQL transformations, and job triggers—into callable tools for Claude, Cursor, CrewAI, LangChain, Amazon Q, and more.

• Storage: Query tables directly and manage table or bucket descriptions
• Components: Create, List and inspect extractors, writers, data apps, and transformation configurations
• SQL: Create SQL transformations with natural language
• Jobs: Run components and transformations, and retrieve job execution details
• Metadata: Search, read, and update project documentation and object metadata using natural language

Make sure you have:

• Python 3.10+ installed
• Access to a Keboola project with admin rights
• Your preferred MCP client (Claude, Cursor, etc.)

Note: Make sure you have uv installed. The MCP client will use it to automatically download and run the Keboola MCP Server. Installing uv:

macOS/Linux:

# Using the installer script
curl -LsSf https://astral.sh/uv/install.sh | sh

# Or using pip
pip install uv

# Or using Homebrew
brew install uv

Windows:

# Using the installer script
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Or using pip
pip install uv

# Or using winget
winget install --id=astral-sh.uv -e

For more installation options, see the official uv documentation.

Before setting up the MCP server, you need three key pieces of information:

This is your authentication token for Keboola:

For instructions on how to create and manage Storage API tokens, refer to the official Keboola documentation.

Note: If you want the MCP server to have limited access, use custom storage token, if you want the MCP to access everything in your project, use the master token.

This identifies your workspace in Keboola and is required for SQL queries:

Follow this Keboola guide to get your KBC_WORKSPACE_SCHEMA.

Note: Check Grant read-only access to all Project data option when creating the workspace

Your Keboola API URL depends on your deployment region. You can determine your region by looking at the URL in your browser when logged into your Keboola project:

If your Keboola project uses BigQuery backend, you will need to set GOOGLE_APPLICATION_CREDENTIALS environment variable in addition to KBC_STORAGE_TOKEN and KBC_WORKSPACE_SCHEMA:

1. Go to your Keboola BigQuery workspace and display its credentials (click Connect button)
2. Download the credentials file to your local disk. It is a plain JSON file
3. Set the full path of the downloaded JSON credentials file to GOOGLE_APPLICATION_CREDENTIALS environment variable
4. This will give your MCP server instance permissions to access your BigQuery workspace in Google Cloud Note: KBC_WORKSPACE_SCHEMA is called Dataset Name in the BigQuery workspace, you simply click connect and copy the Dataset Name.

There are four ways to use the Keboola MCP Server, depending on your needs:

In this mode, Claude or Cursor automatically starts the MCP server for you. You do not need to run any commands in your terminal.

1. Configure your MCP client (Claude/Cursor) with the appropriate settings
2. The client will automatically launch the MCP server when needed

1. Go to Settings → Developer → Edit Config (if you don't see the claude_desktop_config.json, create it)
2. Add the following configuration:
3. Restart Claude desktop for changes to take effect

{
  "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"
      }
    }
  }
}

Note: For BigQuery users, add the following line into "env": {}: "GOOGLE_APPLICATION_CREDENTIALS": "/full/path/to/credentials.json"

Config file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

1. Go to Settings → MCP
2. Click "+ Add new global MCP Server"
3. Configure with these settings:

{
  "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"
      }
    }
  }
}

Note: For BigQuery users, add the following line into "env": {}: "GOOGLE_APPLICATION_CREDENTIALS": "/full/path/to/credentials.json"

When running the MCP server from Windows Subsystem for Linux with Cursor AI, use this configuration:

{
  "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'"
      ]
    }
  }
}

Where /wsl_path/to/keboola-mcp-server/.env file contains environment variables:

export KBC_STORAGE_TOKEN="your_keboola_storage_token"
export KBC_WORKSPACE_SCHEMA="your_workspace_schema"

For developers working on the MCP server code itself:

1. Clone the repository and set up a local environment
2. Configure Claude/Cursor to use your local Python path:

{
  "mcpServers": {
    "keboola": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": [
        "-m", "keboola_mcp_server.cli",
        "--transport", "stdio",
        "--api-url", "https://connection.YOUR_REGION.keboola.com"
      ],
      "env": {
        "KBC_STORAGE_TOKEN": "your_keboola_storage_token",
        "KBC_WORKSPACE_SCHEMA": "your_workspace_schema",

      }
    }
  }
}

Note: For BigQuery users, add the following line into "env": {}: "GOOGLE_APPLICATION_CREDENTIALS": "/full/path/to/credentials.json"

You can run the server manually in a terminal for testing or debugging:

# Set environment variables
export KBC_STORAGE_TOKEN=your_keboola_storage_token
export KBC_WORKSPACE_SCHEMA=your_workspace_schema
# For BigQuery users
# export GOOGLE_APPLICATION_CREDENTIALS=/full/path/to/credentials.json

# Run with uvx (no installation needed)
uvx keboola_mcp_server --api-url https://connection.YOUR_REGION.keboola.com

# OR, if developing locally
python -m keboola_mcp_server.cli --api-url https://connection.YOUR_REGION.keboola.com

Note: This mode is primarily for debugging or testing. For normal use with Claude or Cursor, you do not need to manually run the server.

docker pull keboola/mcp-server:latest

# For Snowflake users
docker run -it \
  -e KBC_STORAGE_TOKEN="YOUR_KEBOOLA_STORAGE_TOKEN" \
  -e KBC_WORKSPACE_SCHEMA="YOUR_WORKSPACE_SCHEMA" \
  keboola/mcp-server:latest \
  --api-url https://connection.YOUR_REGION.keboola.com

# For BigQuery users (add credentials volume mount)
# docker run -it \
#   -e KBC_STORAGE_TOKEN="YOUR_KEBOOLA_STORAGE_TOKEN" \
#   -e KBC_WORKSPACE_SCHEMA="YOUR_WORKSPACE_SCHEMA" \
#   -e GOOGLE_APPLICATION_CREDENTIALS="/creds/credentials.json" \
#   -v /local/path/to/credentials.json:/creds/credentials.json \
#   keboola/mcp-server:latest \
#   --api-url https://connection.YOUR_REGION.keboola.com

Once your MCP client (Claude/Cursor) is configured and running, you can start querying your Keboola data:

You can start with a simple query to confirm everything is working:

What buckets and tables are in my Keboola project?

Data Exploration:

• "What tables contain customer information?"
• "Run a query to find the top 10 customers by revenue"

Data Analysis:

• "Analyze my sales data by region for the last quarter"
• "Find correlations between customer age and purchase frequency"

Data Pipelines:

• "Create a SQL transformation that joins customer and order tables"
• "Start the data extraction job for my Salesforce component"

Note: Keboola MCP is pre-1.0, so some breaking changes might occur. Your AI agents will automatically adjust to new tools.

⭐ The primary way to get help, report bugs, or request features is by opening an issue on GitHub. ⭐

The development team actively monitors issues and will respond as quickly as possible. For general information about Keboola, please use the resources below.

• User Documentation
• Developer Documentation
• Keboola Platform
• Issue Tracker ← Primary contact method for MCP Server

• LinkedIn
• Twitter
• Changelog