Complete AI Training

MCP server · Analytics

Redash MCP server

by seob717

Ask your AI questions in plain English and it runs the SQL in Redash, then shows you the answer.

Flow diagram: you ask your AI “How many new users signed up this month?”, the Redash MCP server connects it to Redash, and you get back A plain answer in your chat.

This is a small helper that connects your AI assistant to Redash, the tool your company uses to look at data and build charts. Once it is set up, you can just type a question like "how many people signed up this month?" and the AI will write the database query, run it in Redash, and tell you the number. It is handy for anyone who needs answers from company data but does not write SQL themselves.

What is an MCP server? The 30-second version

On its own, your AI can only chat. It cannot see your company's data or click around in Redash. An MCP server is a little helper program you install on your own computer that gives your AI a new skill, in this case the skill to talk to Redash. So when you ask a question, the AI passes it to this helper, the helper talks to your Redash account, and the answer comes back into the chat.

What this MCP server does

You ask your AI a question in normal words. The AI uses this helper to look at what data sources and tables exist in your Redash. It picks the right tables, writes the SQL for you, and sends it to Redash to run. Redash returns the rows, and the AI turns them into a plain answer in your chat. You can also use it to list saved queries, look at dashboards, and create new queries, dashboards, widgets, or alerts.

Flow diagram: you ask your AI “How many new users signed up this month?”, the Redash MCP server connects it to Redash, and you get back A plain answer in your chat. Click to zoom

What you can do with it

  • Ask questions about your data in plain English and get numbers back
  • List the tables and columns available in a Redash data source
  • Run a SQL query and see the results in the chat
  • List, open, and run your saved Redash queries
  • Look at dashboards and the widgets on them
  • Create a new saved query or dashboard
  • Set up alerts that fire when a number goes above or below a threshold

Try asking your AI

  • “How many new users signed up this month?”
  • “Show me the columns in the users table”
  • “List all my saved queries”
  • “Create a monthly revenue trend query and add it to a dashboard”

What it gives back to you

You get answers written out in the chat, like a number, a short summary, or a small table of rows. When it creates or changes something in Redash, it tells you what it did and often gives you a link to open it. If it lists queries, dashboards, or alerts, you see them as a simple list.

Before you start

What you need

  • A Redash account with access to the data you want to query
  • Your Redash API key (find it in Redash under your profile, then Edit Profile)
  • The web address of your Redash site, like https://redash.example.com
  • Node.js installed on your computer (the setup command uses npx)

Good to know

It can run queries and change things in Redash, including creating, updating, and archiving queries and dashboards, so double-check what the AI is about to do before you say yes.

Install it with your AI

Add Redash 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 Redash 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.

Sign in Become a member

Who it's for

Anyone who needs answers from company data in Redash but does not want to write SQL, such as analysts, product managers, marketers, and operations folks.