# Keboola MCP server
> Explore Keboola project data, run SQL, and manage transformations, components, flows and jobs from your AI assistant.
- Listing: https://mcp.tc/i/keboola
- Connect: use the server's own URL `https://mcp.keboola.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Databases & Backend](https://mcp.tc/c/databases)
- Vendor: Keboola
- Homepage:
- Repository:
- Package: pypi `keboola-mcp-server`
## About
Connects an AI assistant to a Keboola project. It can query storage tables, edit table and bucket descriptions, create and inspect extractors, writers and SQL transformations, run components and jobs, build flows, and manage Streamlit data apps. Operations can be scoped to a development branch.
Keboola hosts the server on each multi-tenant stack as a streamable HTTP endpoint with OAuth sign-in using your Keboola account. Pick the URL for your region, for example https://mcp.us-east4.gcp.keboola.com/mcp or https://mcp.eu-central-1.keboola.com/mcp. A local option runs with uvx keboola-mcp-server. Headers can restrict tools or enforce read-only mode.
## What it can do
- Query storage tables and update table or bucket descriptions
- Create SQL transformations from natural language
- Create, list and inspect extractors, writers and transformations
- Run components and transformations and read job details
- Build conditional and orchestrator flows
- Create and deploy Streamlit data apps
- Search and update project metadata and documentation
- Work in development branches; limit tools with read-only mode
## Example prompts
- "List my Keboola projects and use the analytics one"
- "Create a SQL transformation that joins orders and customers"
- "Run the latest extractor job and show me its status"
- "Update the description of the sales bucket"
## Install
### Claude Code
1. Run this in a terminal, in your project folder:
```bash
claude mcp add --transport http keboola https://mcp.keboola.com/mcp
```
2. Start Claude Code, type `/mcp`, pick **keboola** and choose **Authenticate**. A browser window opens for the Keboola sign-in.
Add `--scope user` to make it available in every project, not just this one.
### Claude Desktop
1. Open **Settings → Connectors** and click **Add custom connector**.
2. Name it **Keboola** and paste this URL:
```url
https://mcp.keboola.com/mcp
```
3. Click **Add**, then **Connect**, and sign in when Keboola asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
### claude.ai
1. Open the connector form on claude.ai. This button fills in the name and URL for you:
[Add to claude.ai]() (opens connector settings)
2. Check that the URL reads `https://mcp.keboola.com/mcp` and click **Add**.
3. Click **Connect** and sign in when Keboola asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.
### ChatGPT
1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.
2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.
3. Paste `https://mcp.keboola.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Keboola to sign in.
Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.
### Cursor
[Add to Cursor]() (opens Cursor)
Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):
`mcp.json`:
```json
{
"mcpServers": {
"keboola": {
"url": "https://mcp.keboola.com/mcp"
}
}
}
```
Cursor shows **Needs login** next to the server. Click it to sign in.
### VS Code
[Install in VS Code]() (opens VS Code)
Or from a terminal:
```bash
code --add-mcp '{"name":"keboola","type":"http","url":"https://mcp.keboola.com/mcp"}'
```
Or commit it to the repo in `.vscode/mcp.json`:
`.vscode/mcp.json`:
```json
{
"servers": {
"keboola": {
"type": "http",
"url": "https://mcp.keboola.com/mcp"
}
}
}
```
VS Code asks you to sign in the first time the server starts.
### Devin Desktop
1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):
`mcp_config.json`:
```json
{
"mcpServers": {
"keboola": {
"serverUrl": "https://mcp.keboola.com/mcp"
}
}
}
```
2. Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.
### Codex
```bash
codex mcp add keboola --url https://mcp.keboola.com/mcp
codex mcp login keboola
```
Or edit `~/.codex/config.toml` directly:
`config.toml`:
```toml
[mcp_servers.keboola]
url = "https://mcp.keboola.com/mcp"
```
### Gemini CLI
```bash
gemini mcp add --transport http keboola https://mcp.keboola.com/mcp
```
Then, inside Gemini CLI, run `/mcp auth keboola` to sign in.
This adds it to the current project. Add `-s user` to use it everywhere.
### Any client
Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.
```json
{
"mcpServers": {
"keboola": {
"type": "http",
"url": "https://mcp.keboola.com/mcp"
}
}
}
```
Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.
Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.keboola.com/mcp`.
## Details
- Server version: 1.88.6
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03
---
Source: https://mcp.tc/i/keboola (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report