Keboola 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.

Overview

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.

• Quick Start

• Local Setup

Related MCP server: Claude Dev Server

Features

With the AI Agent and MCP Server, you can:

• 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

• Flows: Build and manage workflow pipelines using Conditional Flows and Orchestrator Flows.

• Data Apps: Create, deploy and manage Keboola Streamlit Data Apps displaying your queries over storage data.

• Metadata: Search, read, and update project documentation and object metadata using natural language

• Dev Branches: Work safely in development branches outside of production, where all operations are scoped to the selected branch.

🚀 Quick Start: Remote MCP Server (Easiest Way)

The easiest way to use Keboola MCP Server is through our Remote MCP Server. This hosted solution eliminates the need for local setup, configuration, or installation.

What is the Remote MCP Server?

Our remote server is hosted on every multi-tenant Keboola stack and supports OAuth authentication. You can connect to it from any AI assistant that supports remote SSE connection and OAuth authentication.

How to Connect

1. Get your remote server URL: Navigate to your Keboola Project Settings → MCP Server tab

2. Copy the server URL: It will look like https://mcp.<YOUR_REGION>.keboola.com/sse

3. Configure your AI assistant: Paste the URL into your AI assistant's MCP settings

4. Authenticate: You'll be prompted to authenticate with your Keboola account and select your project

Supported Clients

• Cursor: Use the "Install In Cursor" button in your project's MCP Server settings or click this button

• Claude Desktop: Add the integration via Settings → Integrations

• Windsurf: Configure with the remote server URL

• Make: Configure with the remote server URL

• Other MCP clients: Configure with the remote server URL

For detailed setup instructions and region-specific URLs, see our Remote Server Setup documentation.

Using Development Branches

You can work safely in Keboola development branches without affecting your production data. The remotely hosted MCP Servers respect the KBC_BRANCH_ID parameter and will scope all operations to the specified branch. You can find the development branch ID in the URL when navigating to the development branch in the UI, for example: https://connection.us-east4.gcp.keboola.com/admin/projects/PROJECT_ID/branch/BRANCH_ID/dashboard. The branch ID must be included in each request using the header X-Branch-Id: <branchId>, otherwise the MCP Server uses production branch as default. This should be managed by the AI client or the environment handling the server connection.

Local MCP Server Setup (Custom or Dev Way)

Run the MCP server on your own machine for full control and easy development. Choose this when you want to customize tools, debug locally, or iterate quickly. You’ll clone the repo, set Keboola credentials via environment variables or headers depending on the server transport, install dependencies, and start the server. This approach offers maximum flexibility (custom tools, local logging, offline iteration) but requires manual setup and you manage updates and secrets yourself.

The server supports multiple transport options, which can be selected by providing the --transport <transport> argument when starting the server:

• stdio - Default when --transport is not specified. Standard input/output, typically used for local deployment with a single client.

• streamable-http - Runs the server remotely over HTTP with a bidirectional streaming channel, allowing the client and server to continuously exchange messages. Connect via /mcp (e.g., http://localhost:8000/mcp).

• sse - Deprecated, use streamable-http instead. Runs the server remotely using Server-Sent Events (SSE) for one-way event streaming from server to client. Connect via /sse (e.g., http://localhost:8000/sse).

• http-compat - A custom transport supporting both SSE and streamable-http. It is currently used on Keboola remote servers but will soon be replaced by streamable-http only.

For client–server communication, Keboola credentials must be provided to enable working with your project in your Keboola Region. The following are required: KBC_STORAGE_TOKEN, KBC_STORAGE_API_URL, KBC_WORKSPACE_SCHEMA and optionally KBC_BRANCH_ID. You can provide these in two ways:

• For personal use (mainly with stdio transport): set the environment variables before starting the server. All requests will reuse these predefined credentials.

• For multi-user use: include the variables in the request headers so that each request uses the credentials provided with it.

KBC_STORAGE_TOKEN

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.

KBC_WORKSPACE_SCHEMA

This identifies your workspace in Keboola and is used for SQL queries. However, this is only required if you're using a custom storage token instead of the Master Token:

• If using Master Token: The workspace is created automatically behind the scenes

• If using custom storage token: Follow this Keboola guide to get your KBC_WORKSPACE_SCHEMA

Note: When creating a workspace manually, check Grant read-only access to all Project data option

Note: KBC_WORKSPACE_SCHEMA is called Dataset Name in BigQuery workspaces, you simply click connect and copy the Dataset Name

KBC_STORAGE_API_URL (Keboola Region)

Your Keboola Region 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:

KBC_BRANCH_ID (Optional)

To operate on a specific Keboola development branch, set the branch ID using the KBC_BRANCH_ID parameter. The MCP server scopes its functionality to the specified branch, ensuring all changes remain isolated and do not impact the production branch.

• If not provided, the server uses the production branch by default.

• For development work, set KBC_BRANCH_ID to the numeric ID of your branch (e.g., 123456). You can find the development branch ID in the URL when navigating to the development branch in the UI, for example: https://connection.us-east4.gcp.keboola.com/admin/projects/PROJECT_ID/branch/BRANCH_ID/dashboard.

• On remote transports, you can override per-request with the HTTP header X-Branch-Id: <branchId> or KBC_BRANCH_ID: <branchId>.

Installation

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:

Windows:

For more installation options, see the official uv documentation.

Running Keboola MCP Server

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

Option A: Integrated Mode (Recommended)

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

Claude Desktop Configuration

1. Go to Claude (top left corner of your screen) -> 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

Config file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

• Windows: %APPDATA%\Claude\claude_desktop_config.json

Cursor Configuration

1. Go to Settings → MCP

2. Click "+ Add new global MCP Server"

3. Configure with these settings:

Note: Use short, descriptive names for MCP servers. Since the full tool name includes the server name and must stay under ~60 characters, longer names may be filtered out in Cursor and will not be displayed to the Agent.

Cursor Configuration for Windows WSL

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

Option B: Local Development Mode

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:

Option C: Manual CLI Mode (For Testing Only)

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

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.

Note: The server will use the SSE transport and listen on localhost:8000 for the incoming SSE connections. You can use --port and --host parameters to make it listen elsewhere.

Option D: Using Docker

Note: The server will use the SSE transport and listen on localhost:8000 for the incoming SSE connections. You can change -p to map the container's port somewhere else.

Do I Need to Start the Server Myself?

Using MCP Server

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

Verify Your Setup

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

Examples of What You Can Do

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"

Compatibility

MCP Client Support

Supported Tools

Note: Your AI agents will automatically adjust to new tools.

Troubleshooting

Common Issues

Development

Installation

Basic setup:

With the basic setup, you can use uv run tox to run tests and check code style.

Recommended setup:

With the recommended setup, packages for testing and code style checking will be installed which allows IDEs like VsCode or Cursor to check the code or run tests during development.

Integration tests

To run integration tests locally, use uv run tox -e integtests. NOTE: You will need to set the following environment variables:

• INTEGTEST_STORAGE_API_URL

• INTEGTEST_STORAGE_TOKEN

• INTEGTEST_WORKSPACE_SCHEMA

In order to get these values, you need a dedicated Keboola project for integration tests.

Updating uv.lock

Update the uv.lock file if you have added or removed dependencies. Also consider updating the lock with newer dependency versions when creating a release (uv lock --upgrade).

Updating Tool Documentation

When you make changes to any tool descriptions (docstrings in tool functions), you must regenerate the TOOLS.md documentation file to reflect these changes:

Support and Feedback

⭐ The primary way to get help, report bugs, or request features is by

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

Resources

• User Documentation

• Developer Documentation

• Keboola Platform

• Issue Tracker ← Primary contact method for MCP Server

Connect

• LinkedIn

• Twitter

• Changelog