Skip to main content

AI & ML Integration

Databend enables powerful AI and ML capabilities through two complementary approaches: build custom AI functions with your own infrastructure, or create conversational data experiences using natural language.

External functions enable you to connect your data with custom AI/ML infrastructure, providing maximum flexibility and performance for AI workloads.

FeatureBenefits
Custom ModelsUse any open-source or proprietary AI/ML models
GPU AccelerationDeploy on GPU-equipped machines for faster inference
Data PrivacyKeep your data within your infrastructure
ScalabilityIndependent scaling and resource optimization
FlexibilitySupport for any programming language and ML framework

MCP Server - Natural Language Data Interaction

The Model Context Protocol (MCP) server enables AI assistants to interact with your Databend database using natural language, perfect for building conversational BI tools. On Databend Cloud, point your AI client at the hosted MCP server and sign in through your browser — no DSN or local install required.

FeatureBenefits
Natural LanguageQuery your data using plain English
AI Assistant IntegrationWorks with Claude, Cursor, Codex, and custom agents
OAuth Sign-InConnect with a single URL; no token to manage

Getting Started

External Functions Guide - Learn how to create and deploy custom AI functions with practical examples and implementation guidance

MCP Client Integration - Connect your AI assistant to the hosted Databend Cloud MCP server, or run the local mcp-databend server for self-hosted Databend

MCP Server Guide - Build a conversational BI tool using the local mcp-databend server (also the way to connect self-hosted Databend)

Try Databend Cloud for FREE

Multimodal, object-storage-native warehouse for BI, vectors, search, and geo.

Snowflake-compatible SQL with automatic scaling.

Sign up and get $200 in credits.

Try it today