MCP server · Analytics · official

Datanika MCP server

Let your AI browse your Datanika data connections, preview tables, and check pipeline runs for you.

Analytics For it and development Data Platforms

This is a small helper that connects your AI assistant to Datanika, an open-source platform for moving and transforming data. Once it is set up, you can ask your AI questions about your data connections, tables, and pipeline runs in plain English. It is handy for data analysts, analytics engineers, and anyone who works with dbt models but does not want to click around a dashboard all day.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app. This one connects your AI to Datanika, so it can look up your connections, peek at tables, and check runs for you. You ask in normal words, and the helper does the looking up behind the scenes.

What this MCP server does

You ask your AI something like which tables are in a connection, or how the last pipeline run went. The AI passes your question to this helper. The helper talks to your Datanika account over the internet using a key you gave it. Datanika sends back the answer, and your AI shows it to you in the chat. By default it only reads; it will not change anything unless you turn on write access on purpose.

Flow diagram: you ask your AI “How did my nightly pipeline run go last night?”, the Datanika MCP server connects it to Datanika, and you get back answer shown in your chat.

Click to zoom

What you can do with it

List all your data connections and see their details
Peek at the first rows of a table before you use it
Run a read-only SQL query and see the results
Compile a dbt transformation to check it before running it
Look at recent pipeline and upload runs, with logs
Browse your catalog of source tables and dbt models
Create connections, pipelines, or transformations if you turn on write access

Try asking your AI

“List my Datanika connections and tell me which ones are Postgres”
“Show me the first 10 rows of the orders table in my sales connection”
“How did my nightly pipeline run go last night? Show me the logs”
“Compile my customer_revenue transformation and tell me if there are errors”

What it gives back to you

You get answers in the chat: lists of connections or tables, small tables of preview rows, run statuses with timestamps, and log text when something failed. If you ask it to compile a dbt model, you see whether it worked or what went wrong. With write access on, you also see confirmation that a new resource was created or a run was triggered.

Before you start

What you need

A Datanika account (cloud at app.datanika.io, or your own self-hosted instance)
An API key from Datanika (a kind of password for apps; you create it in your Datanika account)
The Claude desktop app, or another AI app that supports MCP servers
uvx installed on your computer (comes with the uv tool; the README shows the one-line install)

Good to know

By default it only reads, but if you turn on write access it can create connections, pipelines, and transformations and start runs in your Datanika account, so keep it read-only unless you really need the write features.

Install it with your AI

Add Datanika MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Datanika MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.