---
title: MCP toolboxes
slug: mcp-toolboxes
description: Create and manage MCP toolboxes: select and configure tools, generate keys, and connect to MCP clients. 
image: https://archbee-image-uploads.s3.amazonaws.com/oAyFj2GHlBeBVWF5OAir2/gCXC_7mtkmW6Sg6myTKbR_8.png
docTags: 
createdAt: 2026-02-03T09:01:09.716Z
---

MCP toolboxes are dedicated Make MCP servers that allow MCP clients, such as Claude and ChatGPT, to access and use your scenarios. They consist of a specific set of MCP tools (scenarios that you've set to active with on-demand scheduling).

In this guide, learn when to use MCP toolboxes, their key features, and how to work with them in Make and MCP clients.&#x20;

::embed[]{url="https://www.youtube.com/watch?v=rZm-QvQIZ-g"}

## When to use MCP toolboxes

Use MCP toolboxes when:&#x20;

- You want more control over the tools available to MCP clients
- You want a secure way to share MCP tools with team members and clients

Make MCP server is another way to use MCP with Make. To learn more, see [Make MCP server](docId:95jjtReuq1qmRYiBxVBkX).

## Key features&#x20;

MCP toolboxes offer these features:

- Tool management in Make (add, configure, and delete)
- Token-based authorization using keys
- A unique URL per toolbox
- The option to create multiple keys per toolbox for sharing
- Configurable tool labels, descriptions, and types (`Read only` and `Read & write`)

## Create an MCP toolbox

To create an MCP toolbox, including its unique URL and key:

::::WorkflowBlock
:::WorkflowBlockItem
In Make, click **MCP Toolboxes** on the left sidebar, then **Create toolbox&#x20;**&#x61;t the top.&#x20;
:::

:::WorkflowBlockItem
Name your toolbox.&#x20;
:::

:::WorkflowBlockItem
In **Tools**, select the tools you want to have in your toolbox. Only active scenarios with on-demand scheduling appear in the tool list.&#x20;
:::

:::WorkflowBlockItem
Click **Create**.&#x20;
:::

:::WorkflowBlockItem
In the **Create key** dialog, copy the key provided and store it in a safe place.&#x20;
:::

:::WorkflowBlockItem
Click **Close**.&#x20;
:::

:::WorkflowBlockItem
In **MCP Server URL**, copy the URL provided.
:::
::::

You've now created an MCP toolbox in Make.

## Connect your MCP toolbox to an MCP client

Before connecting your MCP toolbox to an MCP client, you must:

- **Choose an MCP client**: Typical options include Claude, ChatGPT, and Cursor.
- **Check what the client supports**: In the client's MCP server documentation, check if the client supports authorization headers and the transport methods available. HTTP Streamable is the recommended method due to its connection reliability.&#x20;

Next, **continue to Step 1&#x20;**&#x74;o configure your URL based on what the client supports.

:::::ExpandableHeading
### Step 1. Configure your URL

You must have a complete MCP server URL to connect to an MCP client.&#x20;

To configure the URL:

::::WorkflowBlock
:::WorkflowBlockItem
Configure your URL based on the following structure, depending on whether the MCP client provides an authorization header.&#x20;

**With authorization headers**

`<MCP TOOLBOX URL>` with the key in the authorization header:

- Header name: Authorization
- Header value: Bearer `<TOOLBOX KEY>`

**Without authorization headers**

`<MCP TOOLBOX URL>`/t/`<TOOLBOX KEY>`/`<TRANSPORT METHOD>`
:::

:::WorkflowBlockItem
Replace the placeholders with your actual values.&#x20;

- `MCP TOOLBOX URL`: The URL generated when you created the MCP toolbox.&#x20;
- `TOOLBOX KEY`: The key generated for the MCP toolbox.&#x20;
- `TRANSPORT METHOD`: The path of your preferred transport method. Stateless Streamable HTTP (`/stateless`) is recommended due to its connection reliability.&#x20;

**Example with authorization headers**

- URL: https\://eu2.make.com/mcp/server/•••••••••••••[ ](https://eu2.make.com/mcp/server/•••••••••••••/t/•••••••••••••/stateless)(`MCP TOOLBOX URL`)
- Authorization header: ••••••••••••• (`TOOLBOX KEY`)

**Example without authorization headers**

- URL: https\://eu2.make.com/mcp/server/•••••••••••••/t/•••••••••••••/stateless (`MCP TOOLBOX URL`/t/`TOOLBOX KEY`/`TRANSPORT METHOD`)
:::
::::

You've now configured your MCP toolbox URL. You'll add it when you're connecting to an MCP client.&#x20;
:::::

:::::ExpandableHeading
### Step 2. Connect to any MCP client

To connect an MCP toolbox to an MCP client:

::::WorkflowBlock
:::WorkflowBlockItem
In your MCP toolbox, in **MCP Server URL**, click **Connect with...&#x20;**&#x61;nd select an MCP client. If you don't see your preferred client, open its documentation for adding remote MCP servers.&#x20;
:::

:::WorkflowBlockItem
In the documentation, begin following the steps for connecting to your client.
:::

:::WorkflowBlockItem
When asked for a URL, add the URL that you configured in Step 1. If applicable, add the key in the authorization header.&#x20;
:::

:::WorkflowBlockItem
Finish the steps.&#x20;
:::
::::

You've now connected your MCP toolbox to MCP client.
:::::

## Manage your MCP toolbox

Once you create an MCP toolbox, you can add or edit tools, add keys, and delete the toolbox.

### Add tools

To add tools to an existing MCP toolbox:

::::WorkflowBlock
:::WorkflowBlockItem
In **MCP Toolboxes**, click an existing toolbox.&#x20;
:::

:::WorkflowBlockItem
In **Tools**, click **Add**.&#x20;
:::

:::WorkflowBlockItem
Search or select a tool or multiple tools.
:::

:::WorkflowBlockItem
Click **Save**.&#x20;
:::
::::

You've now added tools to an existing MCP toolbox.&#x20;

### Configure tools

Optionally, configure your tool's name, description, and behavior:

- **Name and description:** Give your tool a custom tool name and description when its existing ones in Make may confuse an MCP client or prevent it from choosing the tool correctly. By default, the client sees existing names and descriptions, but custom ones replace them.&#x20;
- **Behavior:&#x20;**&#x53;elect `Read only` and `Read & write` as tool annotations. In MCP clients that support them, annotations help clients understand how cautious to be with a tool, such as asking for permission before running it. By default, tools are `Read & write`. Mark a tool as `Read only` if it only reads data rather than making changes, such as adding or deleting. This option helps the client run your tools more quickly.&#x20;

To configure tools:

::::WorkflowBlock
:::WorkflowBlockItem
In **MCP Toolboxes**, click an existing toolbox.&#x20;
:::

:::WorkflowBlockItem
In **Tools**, click the settings icon.
:::

:::WorkflowBlockItem
In **Tool name**, enter a custom tool name, for example, "Watches unread emails." Alternatively, leave the field empty to use the default name.&#x20;
:::

:::WorkflowBlockItem
In **Tool description**, enter a custom tool description, for example, "Watches inbox for unread emails with a Lead label." Alternatively, leave the field empty to use the default description.&#x20;
:::

:::WorkflowBlockItem
In **Behavior**, select `Read only` or `Read & write` from the dropdown.
:::

:::WorkflowBlockItem
Click **Save**.&#x20;
:::
::::

You can go back to configure your tools at any time.&#x20;

### Add keys

Each MCP toolbox can have multiple keys to share or use across MCP clients.&#x20;

To add keys to your MCP toolbox:

::::WorkflowBlock
:::WorkflowBlockItem
In **MCP Toolboxes**, click an existing toolbox.&#x20;
:::

:::WorkflowBlockItem
In **Keys**, click **Add**.&#x20;
:::

:::WorkflowBlockItem
In **Name**, name your key so you can identify it.
:::

:::WorkflowBlockItem
Save the key in a safe place so you can share it later.&#x20;
:::

:::WorkflowBlockItem
Click **Close**.&#x20;
:::
::::

You've now added a key to your toolbox. To delete a key, click the **X** symbol next to the key to delete.&#x20;

### Delete an MCP toolbox

To delete an MCP toolbox:&#x20;

::::WorkflowBlock
:::WorkflowBlockItem
I&#x6E;**&#x20;MCP Toolboxes**, click the three-dot menu next to an existing toolbox.&#x20;
:::

:::WorkflowBlockItem
Click **Delete**.&#x20;
:::

:::WorkflowBlockItem
Click **Delete&#x20;**&#x74;o confirm.&#x20;
:::
::::

You've now deleted an MCP toolbox.&#x20;

:::hint{type="info"}
**MCP toolbox timeout:** Your MCP toolbox scenarios must finish running within 40 seconds. If a scenario runs longer, the connection times out, and no outputs return to the client.
:::

