> For the complete documentation index, see [llms.txt](https://academy.any2info.com/any2info-academy/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/create-agent/mcp.md).

# Mcp

**Category:** Create agent

**Version:** 1.0

**Last updated:** May 17, 2025

**Author:** Any2Info

***

### Description

MCP (Model Context Protocol) servers can be connected to AI agents within AI Studio.\
This allows agents to communicate with external systems and tools through a standardized MCP interface.

MCP servers can be managed from the dedicated **MCP** tab inside AI Studio and can also be attached directly to agents through the agent properties panel.

*<mark style="color:$danger;">MCP support is currently only available for OpenAI-based AI agents.</mark>*

***

### Before You Start

Before an MCP server can be configured, a valid connection for the MCP server must first be created in the platform.

Connections are managed centrally and are reused for authentication and secure communication with external systems.

Navigate to:

```
Data Studio → Connections
```

***

### Creating a Connection

1. Navigate to **Data Studio → Connections**
2. Click **Add Connection**
3. Configure the connection settings
4. Save the connection

### Setting Secret Values

After creating the connection, the actual secret values (such as API keys or tokens) must be configured separately.

This ensures sensitive information is stored securely and is not directly visible in the connection configuration.

### Steps

1. Navigate to **Data Studio → Connections**
2. Locate the created connection
3. Click the **three-dot menu**
4. Select **Set values**
5. Enter the required secret values

A dialog will open showing the configured headers where the secret values can be entered.

***

### Opening MCP Management

Navigate to:

```
AI Studio → MCP
```

The MCP overview displays all configured MCP servers.

<figure><img src="/files/MG4kJIarqDAgIzdEybDN" alt=""><figcaption></figcaption></figure>

***

### Creating an MCP Server

Click the **+** button inside the MCP tab to create a new MCP server.

The following dialog will open:

| Property   | Description                                          |
| ---------- | ---------------------------------------------------- |
| Name       | Display name of the MCP server                       |
| Url        | URL endpoint of the MCP server                       |
| Connection | Connection used for authentication and communication |

<figure><img src="/files/D1imk4c2BndWdFXSLlOD" alt=""><figcaption></figcaption></figure>

***

### Security Notice

When connecting to external MCP servers, data may be shared with external systems.

Only use trusted MCP endpoints and avoid sharing sensitive information without proper authorization.

***

### Using MCP Servers in Agents

Configured MCP servers can be attached to AI agents through the agent configuration.

Navigate to:

```
AI Studio → Agents
```

Open an agent and expand the **MCP** section inside the properties panel.

Available MCP servers can then be selected from the **MCP servers** dropdown.

<figure><img src="/files/LyBlf5PwxzFnZ2Sbjwma" alt=""><figcaption></figcaption></figure>

***

### Features

* Connect external MCP-compatible systems
* Reuse MCP servers across multiple agents
* Configure secure authenticated connections
* Extend AI agents with external tools and integrations

### Changelog

| Version | Date         | Change                               |
| ------- | ------------ | ------------------------------------ |
| 1.0     | May 17, 2026 | Initial documentation version added. |


---

# 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://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/create-agent/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.