> For the complete documentation index, see [llms.txt](https://docs.aloop.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aloop.icustomer.ai/iharness/bring-your-own-agent.md).

# Bring your own agent

Bring your own agent: connect an external agent to iCustomer through MCP, with the same context and the same record as your team.

The platform is built to be operated by agents as well as people. Your own agent connects through **MCP** (Model Context Protocol) and asks the same questions your team asks in the app, over a wire instead of a screen.

## What your agent gets

* **The same context.** It reads the same Growth Brain your team works from, scoped to your workspace.
* **The same record.** Anything it does lands in the same decision traces, under the same [gates](/iharness/gates.md). An external agent never gets more authority than the person who connected it.
* **The same guardrails.** Suppression, consent, and the one-cadence-per-contact rule apply to agents exactly as they apply to plays.

## Connecting

iCustomer connects as a custom connector, the standard way any remote MCP server is added to an agent.

{% stepper %}
{% step %}

### Open your agent's connector settings

In Claude, open [Add custom connector](https://claude.ai/new?redirect=claude.com\&modal=add-custom-connector#settings/customize-connectors). Other agents have the same option under their MCP or connector settings.
{% endstep %}

{% step %}

### Add iCustomer

Name: **iCustomer**. Remote MCP server URL: `https://mcp.icustomer.ai/mcp`.
{% endstep %}

{% step %}

### Connect

Select **Connect** and sign in with your iCustomer account. That authorizes your agent for your workspace.
{% endstep %}

{% step %}

### Ask away

Your agent now works with your Growth Brain. Try: "Who went Hot this week, and why?"
{% endstep %}
{% endstepper %}

## Your agent and iHarness's agents

iHarness runs its own agents on the inside. They are predefined, and you do not create or curate them. Your own agent connects in from the outside through MCP and works with the same context. See [Surfaces](/concepts/surfaces.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://docs.aloop.icustomer.ai/iharness/bring-your-own-agent.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.