# MaxKB

> MCP Server

Here are a few options, prioritizing clarity and SEO:

*   **MaxKB: Enterprise AI assistant w/ RAG, workflows, & MCP tool use. Open-source.** (75 characters)
*   **MaxKB: Open-source AI assistant for 

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 22254
- **Forks:** 2201
- **Owner:** 1Panel-dev
- **GitHub:** https://github.com/1Panel-dev/MaxKB
- **Homepage:** https://maxkb.pro/
- **Created:** 2023-09-14T02:05:12+00:00
- **Updated:** 2025-07-07T15:29:10+00:00
- **Source:** https://model-context-protocol.com/servers/maxkb

## Setup

## Setup

This guide provides instructions for setting up MaxKB using Docker.

### Prerequisites

*   Docker installed on your system.  Refer to the official Docker documentation for installation instructions: [https://docs.docker.com/get-docker/](https://docs.docker.com/get-docker/)

### Installation

1.  **Run the Docker container:**

    Execute the following command in your terminal to download and run the MaxKB Docker container:

    ```bash
    docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/var/lib/postgresql/data -v ~/.python-packages:/opt/maxkb/app/sandbox/python-packages 1panel/maxkb
    ```

    **Explanation of Docker command options:**

    *   `-d`: Runs the container in detached mode (background).
    *   `--name=maxkb`: Assigns the name "maxkb" to the container.
    *   `--restart=always`:  Ensures the container restarts automatically if it stops.
    *   `-p 8080:8080`: Maps port 8080 on your host machine to port 8080 inside the container.  This allows you to access the MaxKB web interface.
    *   `-v ~/.maxkb:/var/lib/postgresql/data`:  Creates a volume mapping. This persists the PostgreSQL database data to the `~/.maxkb` directory on your host machine. This is important to prevent data loss when the container is stopped or removed.
    *   `-v ~/.python-packages:/opt/maxkb/app/sandbox/python-packages`: Creates a volume mapping. This persists the python packages to the `~/.python-packages` directory on your host machine. This is important to prevent reinstalling packages when the container is stopped or removed.
    *   `1panel/maxkb`: Specifies the Docker image to use.

2.  **Access the MaxKB Web Interface:**

    Once the container is running, open your web browser and navigate to `http://your_server_ip:8080`. Replace `your_server_ip` with the IP address or hostname of the machine where Docker is running.

3.  **Login:**

    Use the following default credentials to log in:

    *   Username: `admin`
    *   Password: `MaxKB@123..`

### Configuration

There are no specific configuration steps required immediately after installation. However, you will likely want to configure the following through the web interface:

*   **LLM Models:** Configure the large language models you want to use with MaxKB (e.g., OpenAI, Claude, Gemini, or self-hosted models).
*   **Knowledge Base:**  Upload documents or configure web crawling to populate the knowledge base.
*   **Agents and Workflows:** Define agents and workflows to automate tasks.

### Environment Variables

The provided `docker run` command does not explicitly set any environment variables. However, MaxKB may support environment variables for advanced configuration. Refer to the MaxKB documentation or source code for a complete list of supported environment variables and their usage.  (This information is not available in the provided README).

### Offline Installation (For Chinese Users)

If you encounter issues pulling the Docker image from Docker Hub due to network restrictions, refer to the [离线安装文档](https://maxkb.cn/docs/installation/offline_installtion/) for instructions on offline installation.

## Tools

## Available Tools

MaxKB offers a range of tools and features designed to facilitate the creation and deployment of AI-powered assistants. Here's a breakdown:

*   **RAG (Retrieval-Augmented Generation) Pipeline:**
    *   **What it does:** Enhances the accuracy and reliability of large language models (LLMs) by grounding their responses in relevant knowledge retrieved from external sources. This reduces hallucinations and improves the quality of Q&A interactions.
    *   **Features:**
        *   Direct document uploading.
        *   Automatic crawling of online documents.
        *   Automatic text splitting.
        *   Vectorization (converting text into numerical representations for efficient retrieval).
*   **Agentic Workflow:**
    *   **What it does:** Enables the orchestration of AI processes to handle complex business scenarios. It allows you to define workflows that involve multiple steps, tools, and decision points.
    *   **Features:**
        *   Powerful workflow engine.
        *   Function library (pre-built functions for common tasks).
        *   MCP (Multi-Choice Programming) tool-use capabilities.
*   **Seamless Integration:**
    *   **What it does:** Simplifies the process of integrating MaxKB into existing third-party business systems.
    *   **Benefits:**
        *   Zero-coding integration.
        *   Rapid deployment of intelligent Q&A capabilities.
        *   Enhanced user satisfaction.
*   **Model-Agnostic Support:**
    *   **What it does:** Allows you to use a variety of large language models with MaxKB.
    *   **Supported Models:**
        *   Private models (e.g., DeepSeek, Llama, Qwen).
        *   Public models (e.g., OpenAI, Claude, Gemini).
*   **Multi-Modal Support:**
    *   **What it does:** Enables MaxKB to handle different types of input and output data.
    *   **Supported Modalities:**
        *   Text
        *   Images
        *   Audio
        *   Video

## Related Articles

- [MaxKB: Enterprise AI Assistant with RAG, Workflows, & MCP Server Tool Use](https://model-context-protocol.com/blog/maxkb-enterprise-ai-assistant-with-rag-workflows-mcp-server-mcp-server-guide)