Build robust data workflows, integrations, and analytics on a single intuitive platform.
Keboola MCP server exists for a simple reason — assistants are far more useful when they can act on Keboola directly instead of describing what you should do. Build robust data workflows, integrations, and analytics on a single intuitive platform.
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.
Once Keboola is connected, these are the calls the assistant has available:
Region — API URLKBC_STORAGE_TOKEN — For instructions on how to create and manage Storage API tokens, refer to the [official KeboolaKBC_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 tokenInstallation — The Installation tool exposed by this serverYou will need 8 environment variables: KBC_STORAGE_API_URL, KBC_STORAGE_TOKEN, KBC_WORKSPACE_SCHEMA, KBC_BRANCH_ID, YOUR_REGION, PROJECT_ID, BRANCH_ID, YOUR_KEBOOLA_STORAGE_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Keboola's toolset — Region, KBC_STORAGE_TOKEN, KBC_WORKSPACE_SCHEMA and 1 more — is a fair guide to whether it matches your workflow.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Region | API URL |
| KBC_STORAGE_TOKEN | For instructions on how to create and manage Storage API tokens, refer to the [official Keboola documentation](https://help.keboola.com/management/project/tokens/). |
| 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: |
| Installation | The Installation tool exposed by this server. |
{
"mcpServers": {
"keboola": {
"command": "uvx",
"args": ["keboola_mcp_server --transport <transport>"],
"env": {
"KBC_STORAGE_API_URL": "https://connection.YOUR_REGION.keboola.com",
"KBC_STORAGE_TOKEN": "your_keboola_storage_token",
"KBC_WORKSPACE_SCHEMA": "your_workspace_schema",
"KBC_BRANCH_ID": "your_branch_id_optional"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| KBC_STORAGE_API_URL | Endpoint or connection string the server talks to. | Yes |
| KBC_STORAGE_TOKEN | Credential the server authenticates with. | Yes |
| KBC_WORKSPACE_SCHEMA | Configuration value read at startup. | Optional |
| KBC_BRANCH_ID | Configuration value read at startup. | Optional |
| YOUR_REGION | Configuration value read at startup. | Optional |
| PROJECT_ID | Configuration value read at startup. | Optional |
| BRANCH_ID | Configuration value read at startup. | Optional |
| YOUR_KEBOOLA_STORAGE_TOKEN | Credential the server authenticates with. | Yes |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Model Context Protocol (MCP) tool to interact with Claude Desktop on macOS
Upload, search, transform and organise your Cloudinary media library from a chat window