Open WebUI Knowledge Base MCP Server
MCP server that exposes Open WebUI Knowledge Bases as tools and resources, enabling AI assistants to search and access knowledge bases.
README
Open WebUI Knowledge Base MCP Server
<div align="center">
MCP server for Open WebUI Knowledge Bases – Search and access your knowledge bases from Cursor, Claude Desktop, and other MCP clients
Features • Quick Start • Usage • Available Tools • Contributing
</div>
An MCP (Model Context Protocol) server that exposes Open WebUI Knowledge Bases as tools and resources, enabling AI assistants like Cursor and Claude Desktop to search and access knowledge bases.
Features
- 🔍 Semantic Search - Search knowledge bases using semantic search
- 📚 Knowledge Base Management - List and get information about knowledge bases
- 👥 Multi-User Support - Each connection uses its own API token for isolation
- 🌐 Dual Transport Modes - Supports both stdio (local) and HTTP (remote) transports
- 🔒 Secure - Per-connection authentication, input validation, rate limiting, CORS protection
Quick Start
Prerequisites
- Python 3.8+ or Docker
- Open WebUI instance with API access
- API token from Open WebUI (Settings → Account → API keys)
Installation
pip install -r requirements.txt
Or using uvx:
pip install uv # or: brew install uv
uvx --from . python mcp_server.py
Usage
stdio Mode (Local)
export OPEN_WEBUI_API_URL="https://your-open-webui-instance.com/api/v1"
export OPEN_WEBUI_API_TOKEN="sk-your-token-here"
python mcp_server.py
HTTP Mode (Production)
Docker Compose:
# Create .env file
echo "OPEN_WEBUI_API_URL=https://your-open-webui-instance.com/api/v1" > .env
# Start server
docker-compose up -d
# View logs
docker-compose logs -f
Direct Python:
export OPEN_WEBUI_API_URL="https://your-open-webui-instance.com/api/v1"
export MCP_TRANSPORT="http"
export MCP_HTTP_PORT="8001"
python mcp_server.py
Server endpoints:
- MCP:
http://localhost:8001/mcp - Health:
http://localhost:8001/health
Configuring Cursor to use your MCP server
Cursor: stdio Mode
Edit ~/.cursor/mcp.json:
{
"mcpServers": {
"open-webui-knowledge": {
"command": "uvx",
"args": ["--from", "/path/to/open-webui-mcp-server", "python", "/path/to/open-webui-mcp-server/mcp_server.py"],
"env": {
"OPEN_WEBUI_API_URL": "https://your-open-webui-instance.com/api/v1",
"OPEN_WEBUI_API_TOKEN": "sk-your-token-here"
}
}
}
}
Cursor: HTTP Mode
{
"mcpServers": {
"open-webui-knowledge": {
"url": "http://localhost:8001/mcp",
"headers": {
"Authorization": "Bearer sk-your-token-here"
}
}
}
}
Available Tools
-
list_knowledge_bases- List all accessible knowledge bases -
search_knowledge_base- Search a knowledge base using semantic searchknowledge_base_id(required): The ID of the knowledge basequery(required): Your search queryk(optional): Number of results (default: 5)
-
get_knowledge_base_info- Get detailed information about a knowledge baseknowledge_base_id(required): The ID of the knowledge base
Environment Variables
| Variable | Description | Default |
|---|---|---|
OPEN_WEBUI_API_URL |
Open WebUI API base URL | Required |
OPEN_WEBUI_API_TOKEN |
Default API token (optional) | None |
MCP_TRANSPORT |
Transport mode: stdio or http |
stdio |
MCP_HTTP_HOST |
HTTP server host | 0.0.0.0 |
MCP_HTTP_PORT |
HTTP server port | 8001 |
MCP_CORS_ORIGINS |
Comma-separated CORS origins (empty = no CORS) | Empty |
MCP_RATE_LIMIT_PER_IP |
Rate limit per IP (e.g., "1000/minute") | 1000/minute |
MCP_RATE_LIMIT_PER_TOKEN |
Rate limit per token | 1000/minute |
MCP_RATE_LIMIT_HEALTH |
Rate limit for health endpoint | 10/minute |
Security
- Input validation and sanitization
- Rate limiting (per-IP and per-token)
- CORS protection (disabled by default)
- Request size limits (10MB max)
- Error message sanitization
- Token validation
Contributing
See CONTRIBUTING.md for development setup and guidelines.
License
This project is licensed under the MIT License.
<div align="center">
Built with ❤️ by Ronas IT
Professional development services • Open source contributors
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。