Can every Databricks user add fenbs?

No. Registration needs a Unity Catalog-enabled workspace, Workspace access and the required catalog, schema, service and connection permissions. An admin can grant the necessary permissions; consumer access alone is not enough.

Does this work in every Databricks region?

Do not assume so. The workspace needs a Model Serving-supported region and Genie Code availability, with partner-powered AI enabled. Check the requirements for your cloud and workspace region.

Why is fenbs missing from the UC MCP Service list?

Ask your admin to check that registration is complete and that you have access to both the connection and the MCP service.

Can I register a local stdio server instead?

The external registration path documented here requires Streamable HTTP. It does not describe running a local stdio command from your laptop.

Connect Databricks to your fenbs kanban board

An admin, or a member with the required Unity Catalog permissions, must register fenbs before Genie Code can use it. The workspace needs supported regional features and partner-powered AI turned on.

Last checked October 28, 2026

Connect Databricks to fenbs

This setup needs an admin or a member with the required Unity Catalog permissions. Your workspace needs Unity Catalog and Workspace access, Model Serving and Genie Code in its region, and partner-powered AI features turned on. Registration requires USE CATALOG, USE SCHEMA, CREATE SERVICE and the documented connection privileges; ordinary consumer access cannot register a server.

Open Unity Gateway, then MCPs. Choose + MCP, then Connect an existing MCP server.
Choose a catalog and schema, name the service fenbs, and choose Create new connection. Enter the MCP URL below.
Choose Dynamic Client Registration for sign-in, then Create & load tools. Choose Login when asked, sign in to fenbs and approve. Choose Create MCP Service.
Open Genie Code Settings, then MCP Servers, then Add Server. Choose UC MCP Service, select fenbs and choose Save.
Ask Genie Code: “What is on my fenbs kanban board?”

The MCP server URL

https://fenbs.ai/api/mcp

Databricks documents the registration and permissions (opens in a new tab), HTTP sign-in setup (opens in a new tab) and Genie Code connection (opens in a new tab). If fenbs is missing, ask your admin for access to the connection and MCP service. These instructions use the AWS documentation; check the requirements for your cloud and region. Set it up in fenbs.

What to save from a Databricks session, and how the next AI picks it up

Before ending work in Genie Code, ask it to save a short account in fenbs. Record the conclusion a person can review: which task moved forward, what was checked, what remains uncertain and the next action. Keep the explanation useful without copying account data or credentials into it.

The change to code, a query or a pipeline and where to find it.
What was run and the result, or what still needs checking.
A decision you made and the reason behind it.
The next step and any permission or answer it needs.

At the next session, ask the connected AI to read fenbs before it starts. Genie Code or another connected assistant can work from those saved conclusions. This carries the account of the work forward; the Databricks data, code and access controls remain in Databricks.

How fenbs helps

Never lose the work you did in an AI session

After a useful AI session, save it in fenbs: the key observations, findings, research and context. Then carry on from exactly where you left off, on any device and in any other AI. The next AI you connect reads it at the start of the session, so you never have to explain the same problem again.

Create a free account

Free for up to 5 people and 50 open tasks · No credit card · Works with Claude, ChatGPT, Cursor and more

Keep the workspace requirements in view

The external registration path requires Streamable HTTP and network access to the server. Databricks governs which sources are available, and each user needs permission to use the service. Genie Code is the current coding-assistant name in the Databricks documentation (opens in a new tab); older pages may call it Databricks Assistant.