4,000+ servers built on vurb.ts
Vinkius

Cube.dev MCP Server for VS Code CopilotGive VS Code Copilot instant access to 15 tools to Check Live, Check Ready, Convert Query, and more

MCP Inspector GDPR Free for Subscribers

GitHub Copilot in VS Code is the most widely adopted AI coding assistant, embedded directly into the world's most popular code editor. With MCP support in Agent mode, Copilot can access external data and APIs to generate context-aware code grounded in real-time information.

Ask AI about this MCP Server for VS Code Copilot

The Cube.dev MCP Server for VS Code Copilot is a standout in the Brain Trust category — giving your AI agent 15 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
Classic Setup·json
{
  "mcpServers": {
    "cubedev": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}
RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Cube.dev and 4,000+ MCP Servers from a single visual interface.

Vinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop Interface
Download Free Open SourceNo signup required
Cube.dev
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cube.dev MCP Server

Connect your Cube.dev instance to any AI agent to bridge the gap between natural language and your data warehouse. This server allows your agent to interact with Cube's semantic layer, ensuring consistent metrics and high-performance data retrieval.

GitHub Copilot Agent mode brings Cube.dev data directly into your VS Code workflow. With a project-scoped config, the entire team shares access to 15 tools. Copilot queries live data, generates typed code, and writes tests from actual API responses, all without leaving the editor.

What you can do

  • Data Querying — Execute complex REST API queries using load_query to fetch aggregated data with measures, dimensions, and filters.
  • SQL Inspection — Use get_sql and execute_cube_sql to debug or run raw queries against the SQL API for deep data investigation.
  • Metadata Exploration — Retrieve cube definitions, views, and segments via get_meta to understand your data model without leaving the chat.
  • Performance Management — Trigger and monitor background pre-aggregation builds with trigger_pre_aggregation_job to ensure your dashboards stay fast.
  • Cloud Management — List deployments and environments if using Cube Cloud to manage your infrastructure context.

The Cube.dev MCP Server exposes 15 tools through the Vinkius. Connect it to VS Code Copilot in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 15 Cube.dev tools available for VS Code Copilot

When VS Code Copilot connects to Cube.dev through Vinkius, your AI agent gets direct access to every tool listed below — spanning semantic-layer, data-modeling, sql-api, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

check

Check live on Cube.dev

Check if Cube deployment is live

check

Check ready on Cube.dev

Check if Cube deployment is ready

convert

Convert query on Cube.dev

Convert a SQL query to a REST API query format

execute

Execute cube sql on Cube.dev

Execute a raw SQL query against the SQL API

generate

Generate meta token on Cube.dev

Requires CUBE_CLOUD_API_KEY. Generate a JWT for the Metadata API

get

Get entity on Cube.dev

Get detailed metadata for a specific entity

get

Get meta on Cube.dev

Get metadata for cubes and views

get

Get pre aggregation job status on Cube.dev

Get status of pre-aggregation jobs

get

Get sql on Cube.dev

Useful for debugging. Get generated SQL for a Cube query

list

List data sources on Cube.dev

List configured data sources

list

List deployments on Cube.dev

Requires CUBE_CLOUD_API_KEY. List all Cube Cloud deployments

list

List entities on Cube.dev

List all cubes and views

list

List environments on Cube.dev

Requires CUBE_CLOUD_API_KEY. List environments for a deployment

load

Load query on Cube.dev

Use this to get aggregated data. Execute a Cube query and return results

trigger

Trigger pre aggregation job on Cube.dev

Trigger a pre-aggregation build job

Connect Cube.dev to VS Code Copilot via MCP

Follow these steps to wire Cube.dev into VS Code Copilot. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Create MCP config

Create a .vscode/mcp.json file in your project root
02

Add the server config

Paste the JSON configuration above
03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
04

Start using Cube.dev

Ask Copilot: "Using Cube.dev, help me...". 15 tools available

Why Use VS Code Copilot with the Cube.dev MCP Server

GitHub Copilot for Visual Studio Code provides unique advantages when paired with Cube.dev through the Model Context Protocol.

01

VS Code is used by over 70% of developers. adding MCP tools to Copilot means your team can leverage external data without leaving their primary editor

02

Project-scoped MCP configs (`.vscode/mcp.json`) let you commit server configurations to your repository, ensuring the entire team shares the same tool access

03

Copilot's Agent mode integrates MCP tools seamlessly with file editing, terminal commands, and workspace search in a single agentic loop

04

GitHub's enterprise compliance and audit features extend to MCP tool usage, providing visibility into how AI interacts with external services

Cube.dev + VS Code Copilot Use Cases

Practical scenarios where VS Code Copilot combined with the Cube.dev MCP Server delivers measurable value.

01

Live API integration: Copilot can query an MCP server, inspect the response schema, and generate typed API client code in the same step

02

DevSecOps workflows: security teams can give developers access to domain intelligence tools directly in their editor for real-time vulnerability assessment during code review

03

Data pipeline development: Copilot fetches sample data via MCP and generates transformation scripts, validators, and test fixtures from actual API responses

04

Documentation generation: Copilot queries available tools and auto-generates README sections, API reference docs, and usage examples

Example Prompts for Cube.dev in VS Code Copilot

Ready-to-use prompts you can give your VS Code Copilot agent to start working with Cube.dev immediately.

01

"Show me the metadata for all available cubes and views."

02

"Run a query to get the total count of orders grouped by status for the last 30 days."

03

"Trigger a pre-aggregation build for the 'Sales' cube."

Troubleshooting Cube.dev MCP Server with VS Code Copilot

Common issues when connecting Cube.dev to VS Code Copilot through Vinkius, and how to resolve them.

01

MCP tools not available

Ensure you are in Agent mode in Copilot Chat. MCP tools only appear in Agent mode.

Cube.dev + VS Code Copilot FAQ

Common questions about integrating Cube.dev MCP Server with VS Code Copilot.

01

Which VS Code version supports MCP?

MCP support requires VS Code 1.99 or later with the GitHub Copilot extension. Ensure both are updated to the latest version. Older versions of Copilot may not expose the Agent mode toggle.
02

How do I switch to Agent mode?

Open the Copilot Chat panel and look for two mode options: "Ask" and "Agent". Click "Agent" to enable autonomous tool calling. In Ask mode, Copilot provides conversational answers but cannot invoke MCP tools.
03

Can I restrict which MCP tools Copilot can access?

Yes. VS Code shows a tool consent dialog before any MCP tool is invoked for the first time. You can also configure tool access policies at the organization level through GitHub Copilot settings.
04

Does MCP work in VS Code Remote or Codespaces?

Yes. MCP servers configured via .vscode/mcp.json work in Remote SSH, WSL, and GitHub Codespaces environments. The MCP connection is established from the remote host, so ensure the server URL is accessible from that environment.

Explore More MCP Servers

View all →