> 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.md).

# Connecting an MCP server

### Introduction

Connecting **MCP (Model Context Protocol)** servers to sovereign chat environments like **LibreChat** and **OpenWebUI** on the **GLBNXT** platform marks a significant shift from simple chatbots to functional AI agents. By integrating these protocols within GLBNXT’s infrastructure, you can leverage the power of external data and specialized tools without sacrificing data sovereignty or security.

### What is an MCP?

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.

### Why is it useful?

In a professional environment, an LLM is only as good as the information it can access. MCP is useful because it provides:

* **Live Context:** It allows the AI to fetch real-time data (like current stock prices, Jira tickets, or GitHub commits) that wasn't in its original training data.
* **Actionable Agency:** It gives the AI "hands" to perform tasks, such as creating a folder, drafting a document in Notion, or executing a Python script.
* **Security & Boundaries:** MCP servers act as a controlled gatekeeper. You can define exactly which folders or APIs the AI is allowed to see, ensuring it doesn't overstep its permissions.


---

# 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.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.