{
  "markdown": "# Kubit MCP Server\n\n**Warehouse-native analytics meets conversational AI**\n\nBring the full power of Kubit directly into your AI workflow. Query, analyze, and explore your data warehouse through natural language—no complex syntax required.\n\n---\n\n## What is Kubit MCP?\n\nThe Kubit MCP (Model Context Protocol) server transforms how teams interact with their analytics platform. By connecting your AI assistant to Kubit, you can:\n\n- **Explore schemas** - Discover events, properties, and dimensions in natural language\n- **Generate reports** - Create analytical queries through conversation\n- **Export data** - Pull raw data in CSV format for deep analysis  \n- **Search content** - Find existing reports and dashboards instantly\n- **Ask questions** - Get insights without learning query syntax\n\n> **Beta Notice**\n> \n> This server is under active development. You may encounter bugs, performance issues, or rate limits as we continue to improve the platform.\n\n---\n\n## Quick Start\n\n### What You'll Need\n\n| Requirement | Description |\n|-------------|-------------|\n| **Kubit Account** | Active access to a Kubit organization |\n| **AI Client** | MCP-compatible tool (Claude, Cursor, etc.) |\n| **Permissions** | Schema access in your Kubit workspace |\n\n### Connection Steps\n\nSetting up the Kubit MCP server is straightforward:\n\n1. **Add the MCP server** to your AI client configuration\n2. **Use the server URL**: `https://mcp.kubit.ai/mcp`\n3. **Complete OAuth authentication** when prompted\n4. **Start querying** your Kubit data\n\n> **Note:** Check your AI client's documentation for specific MCP server setup instructions.\n\n### Authentication & Access\n\nThe server uses **OAuth 2.0** authentication and respects your existing Kubit permissions. You'll only see data from schemas you already have access to—no additional permissions needed.\n\n---\n\n## Tools & Capabilities\n\nYour AI assistant gains access to five powerful tools:\n\n| Tool | Purpose |\n|------|---------|\n| **`getUserContext`** | Initialize session and retrieve available schemas |\n| **`getSchema`** | Explore events, properties, and dimensions in detail |\n| **`createReport`** | Generate and execute analytical queries |\n| **`getRawData`** | Export CSV data from existing reports |\n| **`searchKubit`** | Find reports and dashboards across your org |\n\n---\n\n## Example Conversations\n\n### Understanding User Behavior\n\n```\n\"Show me conversion funnel for mobile app sign-ups in the last quarter\"\n\"What are the most popular features used by premium users?\"\n\"How has user retention changed month-over-month?\"\n```\n\n### Product Performance\n\n```\n\"What are the top events by volume this week?\"\n\"Show me user engagement trends for the last 30 days\"\n\"Compare conversion rates across different traffic sources\"\n```\n\n### Data Discovery\n\n```\n\"What events and properties are available in the mobile app schema?\"\n\"Show me all custom properties for the checkout event\"\n\"What dimensions can I use for user segmentation?\"\n```\n\n---\n\n## Typical Workflow\n\nHere's how most analysis sessions flow:\n\n```\nInitialize → Explore → Search → Create → Export\n```\n\n1. **Initialize** - Call `getUserContext` to see available schemas\n2. **Explore** - Use `getSchema` to understand events and properties  \n3. **Search** - Check `searchKubit` for existing analyses\n4. **Create** - Generate new reports with custom queries\n5. **Export** - Pull `getRawData` for external analysis\n\n---\n\n## Best Practices\n\n### Crafting Effective Prompts\n\n**Be Specific**  \nInclude time ranges, events, and segments in your questions.\n\n```diff\n- \"Show me users\"\n+ \"Show me active users in the US who signed up last month\"\n```\n\n**Provide Context**  \nExplain what you're trying to understand.\n\n```diff\n- \"What's the conversion rate?\"\n+ \"What's the conversion rate from free trial to paid for users who engaged with feature X?\"\n```\n\n**Reference Schemas**  \nUse schema names when working with multiple data sources.\n\n```diff\n- \"Show me sign-up events\"\n+ \"In the mobile_events schema, show me sign-up events\"\n```\n\n**Break It Down**  \nComplex analyses work better as multiple focused questions.\n\n```diff\n- \"Show me everything about user behavior across all channels with retention and conversion\"\n+ Start with \"Show me user retention by channel\" then follow up\n```\n\n### Performance Optimization\n\n- **Use `searchKubit` first** - Leverage existing analyses before creating new reports\n- **Specify date ranges** - Narrow time windows improve query performance  \n- **Export selectively** - Only use `getRawData` when you need detailed external analysis\n\n### Security & Compliance\n\n| Consideration | What It Means |\n|---------------|---------------|\n| **Permission Model** | You can only access schemas you're authorized to view |\n| **AI Processing** | Third-party AI models will process your query data |\n| **Policy Review** | Confirm your organization allows AI-assisted data analysis |\n\n---\n\n## Troubleshooting\n\n### Common Issues & Solutions\n\n**Authentication Failures**  \nVerify your Kubit credentials and organization name\n\n**No Schemas Available**  \nCheck that you have access to at least one schema in Kubit\n\n**Connection Errors**  \nConfirm you're using the correct server URL: `https://mcp.kubit.ai/mcp`\n\n**Report Generation Issues**  \nVerify the schema and events you're referencing exist using `getSchema`\n\n### Need Help?\n\n- Test with simple queries first to verify your connection\n- Check schema access through the Kubit web interface  \n- Use `getSchema` to confirm available events and properties\n\n---\n\n## Support & Resources\n\n**Documentation**  \n[docs.kubit.ai](https://docs.kubit.ai/) - Complete platform documentation\n\n**Customer Success**  \nContact your Kubit customer success team for assistance\n\n**About Kubit**  \n[kubit.ai](https://kubit.ai) - Learn more about warehouse-native analytics\n\n**MCP Protocol**  \n[modelcontextprotocol.io](https://modelcontextprotocol.io) - Explore the Model Context Protocol\n",
  "bytes": 5903,
  "sha": "ae887fd221ed0bd2cf910d690526856657480d4f02ce454347585f36baf7f9b6",
  "repo_slug": "kubit-ai/mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_kubit_mcp_server_d8acdf59/readme"
}