Open WebUI
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
What is Open WebUI?
Open WebUI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to user-friendly ai interface (supports ollama, openai api, ...)
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- User-friendly AI Interface (Supports Ollama, OpenAI API, ...
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx open-webuiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Open WebUI
Open WebUI is a self-hosted, feature-rich AI platform that provides a browser-based chat interface supporting Ollama, OpenAI-compatible APIs, and a built-in RAG engine — designed to run entirely offline. Its MCP server integration exposes Open WebUI's running instance so AI clients can query local language models, manage conversations, and access document knowledge bases without leaving their coding environment. Engineers and teams use it to run local LLMs like Llama 3 and Mistral privately, with all data staying on-premises, while still being reachable from MCP-compatible tools.
Prerequisites
- Docker and Docker Compose installed, or Python 3.11+ for pip install
- Ollama installed and running locally if you want to serve local models (optional for OpenAI API use)
- At least 4 GiB RAM and 2 CPU cores
- An MCP-compatible client such as Claude Desktop or Claude Code CLI
- OpenAI API key (optional, only if using OpenAI-compatible models instead of Ollama)
Install Open WebUI via Docker (recommended)
Run Open WebUI with Docker. This command maps port 3000 to the container and mounts a persistent volume for the database. Use the Ollama variant if Ollama is running on the same machine.
docker run -d -p 3000:8080 \
--add-host=host.docker.internal:host-gateway \
-v open-webui:/app/backend/data \
--name open-webui \
--restart always \
ghcr.io/open-webui/open-webui:mainAlternative: install via pip
If you prefer a Python install without Docker, use pip with Python 3.11. The server will run at http://localhost:8080.
pip install open-webui
open-webui serveComplete initial setup in the browser
Open http://localhost:3000 (Docker) or http://localhost:8080 (pip) and create your admin account. Then configure your model connections under Settings > Connections.
Add Open WebUI to your MCP client configuration
Register the Open WebUI MCP server in your Claude Desktop config. The server proxies requests to your running Open WebUI instance.
{
"mcpServers": {
"open-webui": {
"command": "npx",
"args": ["open-webui"]
}
}
}Verify connectivity
Restart Claude Desktop and ask it to list available models through Open WebUI. You should see the models that your Open WebUI instance has configured (Ollama models, OpenAI models, or both).
Open WebUI Examples
Client configuration
Claude Desktop config for Open WebUI MCP server using npx, pointing to a local instance.
{
"mcpServers": {
"open-webui": {
"command": "npx",
"args": ["open-webui"],
"env": {
"OPENAI_API_KEY": "your-openai-key-if-needed",
"OLLAMA_BASE_URL": "http://localhost:11434"
}
}
}
}Prompts to try
Example prompts that use Open WebUI's local model and RAG capabilities via MCP.
- "List the models available in my Open WebUI instance"
- "Ask llama3.2 via Open WebUI: explain the difference between TCP and UDP"
- "Search my Open WebUI document library for anything about 'deployment checklist'"
- "Start a new conversation in Open WebUI using the mistral model"
- "What web search providers are configured in my Open WebUI instance?"Troubleshooting Open WebUI
Docker container starts but Open WebUI is not reachable at localhost:3000
Check that the container is running with 'docker ps'. Ensure port 3000 is not already in use by another process. If you used a different host port, update the URL accordingly. Check container logs with 'docker logs open-webui'.
Ollama models are not showing up in Open WebUI
The Docker run command must include --add-host=host.docker.internal:host-gateway so the container can reach Ollama on the host. In Open WebUI settings, the Ollama URL should be http://host.docker.internal:11434, not localhost.
npx open-webui fails or is not recognized as an MCP server
The npx open-webui command is for the pip-installed Open WebUI CLI, not necessarily an MCP server package. Verify the package name and version on npm. If the MCP surface is not available via npx, use the Open WebUI Pipelines plugin (github.com/open-webui/pipelines) which has explicit MCP support.
Frequently Asked Questions about Open WebUI
What is Open WebUI?
Open WebUI is a Model Context Protocol (MCP) server that user-friendly ai interface (supports ollama, openai api, ...) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Open WebUI?
Follow the installation instructions on the Open WebUI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Open WebUI?
Open WebUI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Open WebUI free to use?
Yes, Open WebUI is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Open WebUI Alternatives — Similar Cloud Services Servers
Looking for alternatives to Open WebUI? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Nginx UI
★ 11.2kYet another WebUI for Nginx
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Open WebUI 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 Open WebUI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.