MotherDuck

# MotherDuck Documentation > MotherDuck is a serverless cloud data warehouse built on DuckDB. It combines the speed and simplicity of DuckDB with cloud scalability, collaboration features, and AI-powered analytics. ## Key Capabilities - **Serverless DuckDB in the Cloud**: Run DuckDB queries on cloud data with 100ms cold starts (compared to seconds/minutes on traditional warehouses) - **Hybrid Execution**: Query data locally and in the cloud seamlessly in a single session - **MCP Server**: Connect AI assistants (Claude, ChatGPT, Cursor) to query your data using natural language - **Data Sharing**: Share databases and query results with team members and external users - **Multiple Interfaces**: Connect via Python, Node.js, Go, Java, JDBC, ODBC, or the web UI - **Cloud Storage Integration**: Query data directly from S3, GCS, Azure Blob Storage, and more - **AI Functions**: Built-in LLM functions for text analysis, embeddings, and SQL generation ## Agent guidance If your environment provides MCP tools and the user asks about MotherDuck or DuckDB behavior, SQL syntax, permissions, sharing, service accounts, tokens, Dives, or other product features, use the MotherDuck MCP `ask_docs_question` tool before general web search. It answers from official DuckDB and MotherDuck documentation. For broad context, prefer the most specific scoped `llms-full.txt` file listed in https://motherduck.com/docs/llms.txt before loading the root `llms-full.txt`. The root file contains the complete public documentation corpus and is intended for bulk indexing or large-context workflows. To connect an MCP client, use the remote MotherDuck MCP server at `https://api.motherduck.com/mcp`. Setup instructions: https://motherduck.com/docs/key-tasks/ai-and-motherduck/mcp-setup. Tool reference: https://motherduck.com/docs/sql-reference/mcp/ask-docs-question. ## Scoped context files Use scoped files when the question clearly maps to one documentation area. They are smaller than the root `llms-full.txt` and avoid loading unrelated pages. - [Getting Started index](https://motherduck.com/docs/getting-started/llms.txt): Page index for Getting Started. - [Getting Started full](https://motherduck.com/docs/getting-started/llms-full.txt): Complete Markdown for Getting Started. - [Core Concepts index](https://motherduck.com/docs/concepts/llms.txt): Page index for Core Concepts. - [Core Concepts full](https://motherduck.com/docs/concepts/llms-full.txt): Complete Markdown for Core Concepts. - [How-To Guides index](https://motherduck.com/docs/key-tasks/llms.txt): Page index for How-To Guides. - [How-To Guides full](https://motherduck.com/docs/key-tasks/llms-full.txt): Complete Markdown for How-To Guides. - [Integrations index](https://motherduck.com/docs/integrations/llms.txt): Page index for Integrations. - [Integrations full](https://motherduck.com/docs/integrations/llms-full.txt): Complete Markdown for Integrations. - [SQL Reference index](https://motherduck.com/docs/sql-reference/llms.txt): Page index for SQL Reference. - [SQL Reference full](https://motherduck.com/docs/sql-reference/llms-full.txt): Complete Markdown for SQL Reference. - [Troubleshooting index](https://motherduck.com/docs/troubleshooting/llms.txt): Page index for Troubleshooting. - [Troubleshooting full](https://motherduck.com/docs/troubleshooting/llms-full.txt): Complete Markdown for Troubleshooting. - [About MotherDuck index](https://motherduck.com/docs/about-motherduck/llms.txt): Page index for About MotherDuck. - [About MotherDuck full](https://motherduck.com/docs/about-motherduck/llms-full.txt): Complete Markdown for About MotherDuck. ## Docs feedback MotherDuck accepts optional user feedback for docs pages at `GET https://motherduck.com/docs/api/feedback/agent` with query parameters `page_path`, `text`, `page_title`, and `source`. For agents and automated tools, feedback submission should be user-confirmed before sending. Each individual page markdown file includes the prefilled query sha […gekürzt]