Overview

Mixedbread Documentation

Mixedbread is the platform for integrating fast, multimodal search into your applications, agents, and AI systems. Upload your data in any format and instantly make it searchable with natural language queries.

Vector Stores

Vector Stores are the core of Mixedbread's search platform. They are managed indexes that transform your unstructured data into a searchable knowledge base accessible via API.

Get Started

Quickstart - Create your first Vector Store and start searching
Vector Stores Overview - Learn how Vector Stores work and what makes them unique

CLI

We built our CLI to streamline Vector Store operations for developers. Handle bulk file uploads, sync entire directories, and integrate Vector Store capabilities into your CI/CD pipelines - all from terminal.

Introduction - Get to know our CLI and its capabilities
Installation & Setup - Setup the CLI in your terminal

MCP (Model Context Protocol)

Our MCP Server bridges the gap between AI assistants and your Vector Stores. Enable Claude Desktop, Cursor, Claude Code and other AI assistants to directly search and retrieve context from your knowledge bases during conversations.

Introduction - Understand how our MCP Server enhances your AI workflows
Configuration - Connect your AI assistant to the MCP Server

Inference API

Mixedbread also provides direct access to our embedding and reranking models. These open-source models are loved by millions of developers around the world.

Available Endpoints: Embedding · Reranking

Community

Get help and connect with other developers building with Mixedbread.
Join our Discord for support, follow us on X for updates, or connect on LinkedIn.

Quickstart

Build your AI Search Engine in minutes. Create Vector Stores that understand any data format and provide precise context for your AI applications.

Last updated: September 9, 2025