> For the complete documentation index, see [llms.txt](https://www.cakewalk.security/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.cakewalk.security/docs/ai-agent-access/how-to-guides/agents/all-agents.md).

# All Agents

All Agents is the Admin home for every Agent connecting through Cakewalk. Agents connect freely and there is no approval gate. The table shows the full fleet for review; each row drills into a detail page.

***

### 📖 Key concepts

* **Agent**: An MCP client (Claude, Cursor, Copilot, ChatGPT, Codex) that originates tool calls.
* **Discovery**: New Agents connect freely and enter as Active. No approval gate; Admins review them in the fleet.
* **Status**: **Active**, **Inactive** or **Not Connected**, all system-detected. See [Connection and Agent Statuses](/docs/ai-agent-access/concepts/connection-and-agent-statuses.md).
* **Add a seat**: Pre-register a known Agent for an employee before its first session. The Agent appears as Not Connected until it first connects.

:bulb: *Why this matters*: The fleet view tells Admins exactly what is connecting through the MCP Gateway and what each Agent touches.

***

### 📊 The Agents table

* **Navigation**: Agents → All agents.
* **What you see**: one row per Agent.
  * **Agent name + icon**: from the Agent Catalog.
  * **Sessions (30d)**: Agent session count.
  * **Connections accessed**: icon stack of the top Connections this Agent has touched, with a `+N more` counter.
  * **Last active**: most recent session timestamp.
* **Actions**:
  * **Add a seat**: pre-register a known Agent for an employee. It enters as Not Connected until its first connection.

***

### 🛠 Agent detail

**Navigation**: Agents → All agents → click any row. The detail page opens on the Overview tab.

#### Overview

* **What you see**:
  * **Header**: Agent name, icon and Agent metadata (tagline, description).
  * **Activity summary**: sessions (30d), active users, total tool calls.
  * **Top Connections accessed**: the Connections this Agent has touched, with session counts.
* **Why it matters**: Overview is the single screen for "what does this Agent touch?"

***

### 📋 All Agents at a glance

| Surface          | Where               | What you see / can do                                                    | Why it matters                            |
| ---------------- | ------------------- | ------------------------------------------------------------------------ | ----------------------------------------- |
| **Agents table** | Agents → All agents | The full fleet: sessions, Connections accessed, last active. Add a seat. | What is connecting through the Gateway.   |
| **Overview**     | Agents → row        | Header, activity summary and top Connections accessed for one Agent.     | What a single Agent touches, in one view. |

***

### 🔗 Related pages

* [Agent Activity](/docs/ai-agent-access/how-to-guides/agents/agent-activity.md)
* [All Connections](/docs/ai-agent-access/how-to-guides/connections/all-connections.md)
* [Policies](/docs/ai-agent-access/how-to-guides/policies.md)
* [Connection and Agent Statuses](/docs/ai-agent-access/concepts/connection-and-agent-statuses.md)
* [Audit Log](/docs/ai-agent-access/concepts/audit-log.md)


---

# 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, and the optional `goal` query parameter:

```
GET https://www.cakewalk.security/docs/ai-agent-access/how-to-guides/agents/all-agents.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.