# Kubit

Connects warehouse-native Kubit analytics to your AI environment. Lets you inspect schemas and run analytical queries using natural language.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: Kubit-AI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Kubit-AI/mcp-server
- Updated: 2026-08-04
- HTML: https://affpapa.org/en/nevibecode/mcp/kubit

## What it does

This MCP server links your workspace in Kubit directly to an AI client using the remote endpoint `https://mcp.kubit.ai/mcp`. You can explore schemas and trigger analytical queries without writing SQL. The server provides five core tools: `getUserContext` for session startup, `getSchema` for inspecting properties and dimensions, `createReport` to run ad-hoc queries, `getRawData` to extract CSV files, and `searchKubit` to discover shared dashboards.

Access requires an active Kubit account with schema permissions already granted. Authentication relies on OAuth 2.0, keeping queries strictly inside the boundaries of your organizational profile. Because the project remains in public beta, you might encounter occasional rate limits or performance hiccups during heavy runs.

## Requirements
- Remote server: `https://mcp.kubit.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp-server https://mcp.kubit.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add kubit --url https://mcp.kubit.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "kubit": {
            "url": "https://mcp.kubit.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "kubit": {
            "type": "http",
            "url": "https://mcp.kubit.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http kubit https://mcp.kubit.ai/mcp
```

## When to use it
- inspect event properties and dimensions inside a warehouse schema
- build conversion funnel reports using conversational prompts
- export raw report metrics to CSV files
- locate existing organizational dashboards and charts

## Example prompts
- Show me the sign-up conversion funnel for the mobile app over last quarter
- What custom properties exist inside the checkout event schema?
- Search for retention dashboards across the workspace and pull raw data

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md