> For the complete documentation index, see [llms.txt](https://docs.glbnxt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.glbnxt.com/tutorials/guides/connect-mcp/mcp-openwebui.md).

# 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.

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**.

   <img src="/files/vX07tZCl5bC2aue1GAao" alt="" width="400">
3. Go to **Integrations**, here you will find **Manage Tool Servers**.

   <img src="/files/lisOSR4CeWaDzxmwYDfr" alt="" width="400">
4. Click on the **+** icon, the **Add Connection** screen will pop up.

   <img src="/files/9YD8wYXWEvK8WUv4qY6H" alt="" width="400">
5. Press the **OpenAPI** button at the right upper corner, your screen will look like this.

   <img src="/files/er7zuL5y44s4NZOoB3VF" alt="" width="400">
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.

   <img src="/files/pScgLIsEQexih67os7KF" alt="" width="400">
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.

   <img src="/files/OdEMknSaBj0ePnAkk4Fc" alt="" width="400">
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**.

   <img src="/files/nqwnB206PHfbMaXVoj8H" alt="" width="400">
5. Select **Tools** and enable the MCP server.

   <img src="/files/3icerUMXnNxusChUPfnF" alt="" width="400">
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**.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.glbnxt.com/tutorials/guides/connect-mcp/mcp-openwebui.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.