4,500+ servers built on MCP Fusion
Vinkius
Cube.dev logo
Vinkius
Claude Desktop logo

How to Use the Cube.dev MCP in Claude

Query your semantic layer and debug generated SQL without leaving Claude Desktop through this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Cube.dev MCP on Cursor AI Code Editor MCP Client Cube.dev MCP on Claude Desktop App MCP Integration Cube.dev MCP on OpenAI Agents SDK MCP Compatible Cube.dev MCP on Visual Studio Code MCP Extension Client Cube.dev MCP on GitHub Copilot AI Agent MCP Integration Cube.dev MCP on Google Gemini AI MCP Integration Cube.dev MCP on Lovable AI Development MCP Client Cube.dev MCP on Mistral AI Agents MCP Compatible Cube.dev MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Desktop

Connect Cube.dev MCP to Claude Desktop

Create your Vinkius account to connect Cube.dev to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Pull Aggregated Data via MCP Server

`load_query` grabs aggregated metrics straight from your semantic layer. You ask for revenue by region, and your agent maps that to the correct dimensions and measures. No need to write complex joins or figure out which underlying table holds the truth. `get_entity` pulls the exact metadata for those cubes and views. Claude reads the schema first, figures out what fields exist, and then runs the query. You get accurate, formatted answers instead of guesses about your business logic.

Debug Generated SQL Fast

`get_sql` shows you the exact database query Cube generates under the hood. When a metric looks wrong in your dashboard, you can paste the query parameters into chat and see the raw SQL output immediately. `convert_query` takes standard SQL and turns it into the REST API format Cube expects. This lets you think in traditional database terms while your AI client handles the translation to semantic layer requests.

Manage Pre-aggregations

`trigger_pre_aggregation_job` forces a rebuild of your cached data layers. If you just updated an underlying table and need the dashboard to reflect it, you tell Claude to kick off the job. `get_pre_aggregation_job_status` checks if that build actually finished. You sit back while the agent monitors the queue and notifies you when the fresh data is ready to query.

Setup guide

Set up Cube.dev MCP in Claude Web or Desktop

  1. 1

    Open Claude Settings

    Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

  2. 2

    Add Custom Connector

    Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

  3. 3

    Start a conversation

    Open a new chat. The Cube.dev MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cube.dev MCP in Claude Desktop

Edit `claude_desktop_config.json` and add the Vinkius endpoint token. Restart the app to see the tools appear in your chat.
Yes. `list_deployments` requires your cloud API key to fetch active environments. It reads the exact state of your infrastructure.
You might be missing the `CUBE_CLOUD_API_KEY` in your environment variables. Check your configuration file and ensure the token is valid.
Custom connectors in the browser let you paste the remote MCP URL directly. You skip the local file configuration entirely.
The server transmits aggregated metrics, generated SQL strings, and schema metadata. All traffic routes through the Vinkius V8 isolate sandbox, dropping credentials immediately after authentication.

Start using the Cube.dev MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 15 tools

We've already built the connector for Cube.dev. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 15 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.