MaxKB
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
What is MaxKB?
MaxKB is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🔥 maxkb is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🔥 MaxKB is an open-source platform for building enterprise-g
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx maxkbConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MaxKB
MaxKB (Max Knowledge Brain) is an open-source enterprise platform for building RAG-powered AI agents with knowledge base integration, agentic workflows, MCP tool-use, and support for both private LLMs (DeepSeek, Llama, Qwen) and public APIs (OpenAI, Claude, Gemini). It is deployed as a Docker container and exposes a web interface for uploading documents, configuring retrieval pipelines, designing multi-step agent workflows, and embedding a chatbot into third-party systems with zero additional coding. MaxKB's built-in MCP tool-use capability means agents can call external services and APIs during conversations. Organizations use MaxKB for intelligent customer service, internal knowledge bases, academic research assistants, and enterprise Q&A systems that must stay accurate on proprietary data.
Prerequisites
- Docker and Docker Compose installed and running
- A server or local machine with at least 4GB RAM recommended
- An LLM API key or access to a self-hosted model (e.g., Ollama, DeepSeek, or OpenAI API key)
- An MCP-compatible client for connecting to the MaxKB MCP server interface
- Port 8080 available on the host machine for the MaxKB web interface
Deploy MaxKB with Docker
Pull and start the MaxKB container with Docker. The -v flag mounts a persistent volume at ~/.maxkb to store your knowledge bases, configurations, and vector embeddings across container restarts.
docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkbLog in to the MaxKB web interface
Open http://localhost:8080 in your browser. Log in with the default admin credentials. Change the password immediately after first login for security.
# Default credentials:
# Username: admin
# Password: MaxKB@123..Configure an LLM provider
In the MaxKB admin panel, navigate to Settings > Model Provider and add your LLM. MaxKB supports OpenAI API-compatible endpoints, DeepSeek, Qwen, Llama (via Ollama), Claude, Gemini, and others. Enter the API key and select the model to use for embeddings and inference.
Create a knowledge base and upload documents
Go to Knowledge Base > Create and upload your documents (PDF, Word, Markdown, text, or URLs for web crawling). MaxKB automatically splits, vectorizes, and indexes the content into PostgreSQL with pgvector for semantic search retrieval.
Build an agent and enable MCP tool-use
In the agent builder, connect your knowledge base as a retrieval source, configure the agentic workflow with the desired steps, and add MCP tools to let the agent call external APIs. Test the agent in the preview panel, then publish it as an embeddable widget or API endpoint.
Add the MaxKB MCP server to your AI client configuration
To connect MaxKB as an MCP server to your AI coding assistant, add the server entry to your MCP client's config file. This enables your AI client to call MaxKB's agent capabilities as a tool.
MaxKB Examples
Client configuration
Add this block to your claude_desktop_config.json under the mcpServers key to enable the MaxKB MCP server.
{
"mcpServers": {
"maxkb": {
"command": "npx",
"args": ["maxkb"]
}
}
}Prompts to try
With MaxKB deployed and connected, use these prompts to interact with your knowledge bases and agents.
- "Search my company knowledge base for the refund policy and summarize it"
- "Answer customer questions about our product using the uploaded product manual"
- "Use the MaxKB agent to retrieve information about employee benefits from our HR documents"
- "Build a workflow that searches the knowledge base and then calls an external CRM API for context"Troubleshooting MaxKB
Docker container starts but the web interface at localhost:8080 is not accessible
Check that the container is running with 'docker ps' and that port 8080 is not occupied by another service. If running on a remote server, ensure port 8080 is open in your firewall/security group rules. Check container logs with 'docker logs maxkb' for startup errors.
Document upload succeeds but the agent returns irrelevant answers
Check the chunk size and overlap settings in your knowledge base configuration. For long documents, smaller chunks (500-800 tokens) with some overlap generally improve retrieval accuracy. Also verify the embedding model is the same one used during indexing — mixing embedding models causes poor semantic matches.
LLM API calls fail with authentication errors
In MaxKB Settings > Model Provider, verify the API key, base URL, and model name are correct. For Ollama or self-hosted models, ensure the model server is reachable from within the Docker container (use host.docker.internal instead of localhost for the base URL on macOS/Windows).
Frequently Asked Questions about MaxKB
What is MaxKB?
MaxKB is a Model Context Protocol (MCP) server that 🔥 maxkb is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MaxKB?
Follow the installation instructions on the MaxKB GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MaxKB?
MaxKB works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MaxKB free to use?
Yes, MaxKB is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
MaxKB Alternatives — Similar Business Applications Servers
Looking for alternatives to MaxKB? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MaxKB in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MaxKB?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.