> This page is for Workforce.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Roll out to your fleet

> How the Agent Handler tool rollout and the Gateway model rollout differ, which pages apply to the products you have, and how to verify either one landed.

Agent Handler gives an employee's AI client your approved tools, over an MCP endpoint. Gateway gives it your approved models, over a base URL and a key. They are separate connections that reach a machine by different mechanisms, so they roll out separately and in either order. Start here to find the pages that apply to you.

## Which rollout you are running

|                                 | Tools                                                                | Models                                                                                                                                |
| ------------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| **Product**                     | Agent Handler                                                        | Gateway                                                                                                                               |
| **What reaches the client**     | An MCP endpoint URL                                                  | A base URL, an API key, and a model name                                                                                              |
| **What the employee gets**      | The tools their [Groups](/merge-workforce/provisioning/groups) grant | The models their [routing policy](/merge-workforce/models/routing) allows                                                             |
| **What puts it on the machine** | The AI client's own enterprise policy layer, or the employee         | The [desktop client](/merge-workforce/devices/overview), the [Workforce CLI](/merge-workforce/rollout/workforce-cli), or the employee |
| **Follow**                      | [Roll out tools](/merge-workforce/rollout/tools)                     | [Roll out models](/merge-workforce/rollout/models)                                                                                    |

Neither rollout depends on the other, and no page in this section assumes you are doing both.

## The page to send an employee

[Connect employee AI clients](/merge-workforce/rollout/employee-clients) covers both connections in one place, per client. Send that link rather than maintaining a wiki entry, whether you are deploying centrally or asking employees to configure themselves.

## Verify either one the same way

Configuration pushed is not a connection made, and your MDM cannot tell the two apart. Both rollouts are verified by traffic rather than by deployment reports:

* **Tools:** [Tool calls](/merge-workforce/logs/tool-calls) shows every call an employee's client made, with the employee and the Tool Pack it came through
* **Models:** the [Gateway dashboard](https://gateway.merge.dev) shows requests within a few seconds of the first one, attributed to the employee

In both cases, read the result against your [SCIM](/merge-workforce/provisioning/scim)-synced employee list rather than on its own. A client that received your config and never connected looks exactly like a machine you never reached.

## Next steps

#### [Roll out tools](/merge-workforce/rollout/tools)

Deliver the Workforce MCP endpoint through each AI client's policy layer

#### [Roll out models](/merge-workforce/rollout/models)

Get every employee's AI client routing through Merge Gateway

#### [Connect employee AI clients](/merge-workforce/rollout/employee-clients)

The per-client setup page to send an employee