Connecting an MCP Server to OpenWebUI

Introduction

By linking an MCP server, you give your models the power to execute custom functions, tap into external APIs, and bridge data gaps in real time. Whether you need an assistant that can query documentation databases, run custom scripts, or interact with web endpoints, this integration turns OpenWebUI into a highly customized, production-grade AI workstation.

The Model Context Protocol (MCP) is an open standard that creates a universal bridge between Large Language Models (LLMs) and external data sources.

Traditionally, if you wanted an AI to read your local files, query a database, or check your calendar, you had to build a custom, one-off integration for every specific app. MCP replaces this complexity with a standardized architecture. Instead of teaching the AI how to use a hundred different apps, you simply connect it to an MCP server that speaks a language the AI already understands.

This guide provides a straightforward, step-by-step walkthrough to help you register an HTTP-based MCP server in your OpenWebUI admin console and successfully deploy its tools to your active models in the chat interface.

---

Prerequisites

• Admin rights: Make sure you have access to OpenWebUI with admin or tool management permissions.
• Open OpenWebUI: Open the application from your Dashboard.
• MCP server: Have your own MCP server.

---

Steps

Step 1: Start MCP setup

1. In your OpenWebUI application, click on your User Icon.
2. Select Admin Panel and go to Settings.

   
3. Go to Integrations, here you will find Manage Tool Servers.

   
4. Click on the + icon, the Add Connection screen will pop up.

   
5. Press the OpenAPI button at the right upper corner, your screen will look like this.

   
6. Now you are ready to set up your MCP server.

Step 2: Add an MCP server

1. Configure your MCP in the pop up screen. To give you an idea, there is an example MCP (DeepWiki) in the image below.

   
2. Click on the Verify Connection button, if your connection is working you will see the message Connection successful in the right top corner of your screen.

   
3. Click on Save, in the right top corner the message Connection saved successfully will appear.
4. Go to your chat environment and click on Integrations.

   
5. Select Tools and enable the MCP server.

   
6. You are now able to use your MCP server in the chat environment.

Note: For every model you use, you need to independently enable the MCP server. You can simply do this from your chat environment, as proposed from the fourth step in Step 2: Connect an MCP Server.

---

Need help? Contact the GLBNXT support team or ask a GLBNXT agent to walk you through the setup.