An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Redash to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your SQL queries into conversational insights with any AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 17 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 17 available through Redash.

  1. 01

    Execute query

    This capability starts a new query execution or pulls a result from the cache. You must provide parameters if the query requires them.

  2. 02

    Get job

    This capability checks the status of a specific query task. It returns a query_result_id if the job is successful.

  3. 03

    Archive query

    This capability archives a specific query by its unique ID.

  4. 04

    Get dashboard

    This capability fetches the details of a single dashboard using its slug.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 17 available through Redash.

  1. 05

    Get data source

    This capability retrieves the configuration and details for a specific data source.

  2. 06

    List queries

    This capability returns a list of all queries in your Redash instance.

  3. 07

    Test data source

    This capability tests the connection to a specific data source using its ID.

  4. 08

    Update dashboard

    This capability edits an existing dashboard. You provide the ID and the specific changes you want to make.

Capability set03 / 05

09-11

3 capabilities in this set.

Part of 17 available through Redash.

  1. 09

    Archive dashboard

    This capability archives a dashboard using its slug.

  2. 10

    Create dashboard

    This capability builds a new dashboard object. You just need to provide a unique name for it.

  3. 11

    Create query

    This capability creates a new query object. You'll need to include the query string, a name, and a data source ID.

Capability set04 / 05

12-14

3 capabilities in this set.

Part of 17 available through Redash.

  1. 12

    Get cached query result

    This capability retrieves a cached result for a specific query ID. This only works for non-parameterized queries.

  2. 13

    Get query

    This capability fetches the details of an individual query object using its ID.

  3. 14

    Get query result

    This capability pulls a specific query result using its unique result ID.

Capability set05 / 05

15-17

3 capabilities in this set.

Part of 17 available through Redash.

  1. 15

    List dashboards

    This capability returns a paginated list of all your available dashboards.

  2. 16

    Update data source

    This capability modifies data source settings, such as updating SSH tunnel configurations.

  3. 17

    Update query

    This capability allows you to edit an existing query object by providing its ID and the new changes.

Real work

What teams actually run

01

Rapid Query Iteration

An analyst needs to tweak a SQL statement and immediately see the new results without manual UI navigation.

02

Dashboard Auditing

A BI lead asks the agent to list all dashboards to find outdated or unused visualizations.

03

Connection Troubleshooting

An engineer uses the agent to test if a specific data source connection is still active.

04

Automated Reporting

A user asks the agent to execute a specific query and summarize the findings from the result set.

Automate a task

Put Redash to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Redash works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Redash to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1038ms average. Fast in production.

Redash is checked daily against the live service.

Daily averagePeak 1479ms
Oct 3Today
Fastest day
821ms
Slowest day
1479ms
14-day trend
Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 17 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Redash, so you can see the experience inside your AI.

It does not authenticate your account with Redash. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Redash Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_rRCXZFALibUsor8N9CjThd5ZlbvdaN0QeviiaDQu/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Redash capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "redash-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_rRCXZFALibUsor8N9CjThd5ZlbvdaN0QeviiaDQu/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Redash in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Redash owners hand off.

This MCP is built for anyone who spends their day inside Redash and wants to move faster.

  • 01

    Data Analysts

    They use the agent to iterate on SQL queries and check results without switching browser tabs.

  • 02

    Business Intelligence Leads

    They use the agent to monitor dashboard health and pull quick insights via chat.

  • 03

    Engineers

    They use the agent to test data source connections and manage query objects programmatically.

FAQ

Questions Redash owners ask.

  • 01

    How do I connect my Redash instance?

    You need to provide your Redash Base URL and your API Key when you subscribe to the MCP on Vinkius.

  • 02

    Can I run parameterized queries?

    Yes, you can run parameterized queries as long as you provide the necessary parameters to the execute_query capability.

  • 03

    Does this work with any AI client?

    Yes, this MCP works with any client that supports the Model Context Protocol, such as Claude, Cursor, or Windsurf.

  • 04

    Can I manage my dashboards through the agent?

    Yes, you can use the agent to create, update, list, or archive dashboards.

  • 05

    How do I check if a long query is finished?

    You can use the get_job capability to check the status of a query task.

  • 06

    How do I run a query and get the results?

    Use the execute_query capability. If the query takes time, it returns a job_id. You can then use get_job to check the status, and once successful, use get_query_result with the provided ID to fetch the data.

  • 07

    Can I update the SQL of an existing query through the agent?

    Yes! Use the update_query capability by providing the Query ID and the new SQL string in the query parameter. You can also update the name or data source ID.

  • 08

    How do I find a specific dashboard and its widgets?

    First, use list_dashboards to find the slug of the dashboard you need. Then, use the get_dashboard capability with that slug to retrieve all its configuration details and widgets.

Explore

More in Data Analytics

Suggestions

Connect Redash to Claude, Cursor, ChatGPT & more