# My Agents

My Agents is where you set up and manage your own agents: the AI clients (Cursor, Claude, Copilot and others) that act on your behalf through the MCP Gateway. You see only the agents on your own list. Admins curate the company catalog you add from.

***

### 📖 Key concepts

* **Agent**: An AI client that acts on your behalf, such as Cursor, Claude or Copilot. It accesses apps on your behalf by making tool calls through the MCP Gateway.
* **Agent status**: Active, Inactive or Not Connected. See [Connection and Agent Statuses](/docs/ai-agent-access/concepts/connection-and-agent-statuses.md).
* **Company catalog**: The Agents your Admins have made available. You add the ones you use from it.

:bulb: *Why this matters*: Every tool call your Agents make routes through the MCP Gateway, where Policy decides what is allowed. Setting up and adding Agents here is how you bring the AI clients you use under that governance.

***

### 📋 Your agents list

**Navigation**: My Agents in the left nav.

Your Agents appear as cards, split across four tabs:

* **All agents**: everything on your list.
* **Connected**: Agents you have set up and that are Active.
* **Inactive**: Agents with no sessions in the last 30 days.
* **Not Connected**: Agents you have added but not yet set up.

Each card shows the Agent icon and name, a short description, a status chip and the apps the Agent has accessed in the last 90 days. Use the search box to filter by name, tagline or category.

***

### 🔌 Set up an agent

A card shows **Connect** when the Agent is Not Connected.

1. On the Agent card, select **Connect**.
2. The Set up dialog opens with the install steps for that Agent. The steps depend on the Agent's install method: a deep link, a config file, a guided form or a CLI command.
3. Follow the steps. On the Agent's first heartbeat to the MCP Gateway, its status becomes **Active**.

For the exact install path for each Agent, see [Agent Platforms](/docs/ai-agent-access/connections-and-integrations/agent-platforms.md).

{% hint style="info" %}
The Set up dialog renders the right install method per Agent, so you never have to work out which file to edit or which URL to paste where. If **Connect** is unavailable, your Admin still needs to finish adding that Agent to the catalog.
{% endhint %}

***

### ➕ Add an agent

The company catalog holds the Agents your Admins have set up. To add one to your list:

1. Select **New** at the top of the page.
2. In the **Add agent** panel, search the available Agents by name.
3. Select one or more, then select **Confirm**.

The Agents join your list as **Not Connected**. Set up each one to start using it.

***

### ⋯ More actions

Open the 3-dot menu on any Agent card for **View details**: the Agent's detail panel, with its overview and recent activity.

***

### 🔗 Related pages

* [Agent Platforms](/docs/ai-agent-access/connections-and-integrations/agent-platforms.md): the per-agent install reference
* [All Agents](/docs/ai-agent-access/how-to-guides/agents/all-agents.md) (Admin view)
* [Connection and Agent Statuses](/docs/ai-agent-access/concepts/connection-and-agent-statuses.md)
* [My Connections](/docs/ai-agent-access/how-to-guides/connections/my-connections.md)
* [The MCP Gateway](/docs/ai-agent-access/concepts/the-mcp-gateway.md)


---

# Agent Instructions: 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://www.cakewalk.security/docs/ai-agent-access/how-to-guides/agents/my-agents.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.