> For the complete documentation index, see [llms.txt](https://replai-1.gitbook.io/replai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://replai-1.gitbook.io/replai-docs/features-by-tier/agent-tier.md).

# Agent tier

## Agent tier

**Agent** includes everything in **Answer**.

It adds the ability to work from chat, not just answer.

### What does Agent add?

Agent adds:

* Replai Agent in the dashboard
* Take actions from chat
* Custom HTTP actions and tool calling
* Connect your own tools with MCP
* White-label
* Up to 2,500 new conversations per month

### How much action capacity do you get?

Each assistant can have up to **10 HTTP actions**.

Each assistant can also connect up to **3 MCP servers**.

{% hint style="info" %}
White-label starts on **Agent**.

It is not a Live-only feature.
{% endhint %}

### How do actions stay safe?

Consequential actions require approval before they run.

Replai shows a plain-English summary first.

If there is a charge, Replai shows that too.

Read-only lookups can run without that step.

Replai also keeps a short action audit trail on the assistant.

### When should you choose Agent?

Choose **Agent** when the assistant should answer and then do something useful.

Good fits include ticket creation, CRM updates, and account lookup flows.

### Related links

* [Answer tier](/replai-docs/features-by-tier/answer-tier.md)
* [Live tier](/replai-docs/features-by-tier/live-tier.md)
* [Plans comparison](/replai-docs/features-by-tier/plans-comparison.md)
* [Replai Agent (in-product copilot)](/replai-docs/features-by-tier/replai-copilot.md)
* [Connecting your own tools (MCP)](/replai-docs/features-by-tier/connecting-your-own-tools-mcp.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://replai-1.gitbook.io/replai-docs/features-by-tier/agent-tier.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.