> For the complete documentation index, see [llms.txt](https://docs.ilert.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ilert.com/ai-and-agents/mcp/external/aws.md).

# AWS

Connect an agent to the AWS-hosted MCP server, which exposes AWS documentation and APIs.

AWS hosts a managed MCP server that exposes documentation and APIs to an agent.

#### Prerequisites

* An AWS account with permission to create IAM roles
* AWS's own setup notes: [AWS MCP server](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/mcp-server.html)

The endpoint is fixed per region — `https://aws-mcp.<region>.api.aws/mcp` — and derived from the region you enter. There is no URL field.

#### Setup instructions

{% stepper %}
{% step %}
Make sure you have an AWS user with the permissions the agent should have. Grant read-only access only — the agent never needs to change your AWS resources. Usually it make sense to grant permissions to access CloudWatch and Lambda.
{% endstep %}

{% step %}
Setup a key pair for CLI access for the user in AWS, save the keys in a secure location.
{% endstep %}

{% step %}
Navigate to **Connectors** in the ilert navigation menu, scroll to the **MCP Servers** section and click **Connect** on the **AWS MCP Server** card
{% endstep %}

{% step %}
Fill in:

* **Name:** the name for the connector (defaults to "AWS MCP")
* **Region:** the AWS region to use, e.g. `eu-central-1`
* **Access key ID :** the access key of the AWS user
* **Secret access key :** the secret key of the AWS user
  {% endstep %}

{% step %}
Click **Test connection** to confirm ilert agent can authenticate with the given credentials.
{% endstep %}

{% step %}
Click **Save**
{% endstep %}
{% endstepper %}

#### Connect AWS MCP with agent

To connect AWS MCP with your AI SRE agent:

{% stepper %}
{% step %}
Navigate to **Agents** in the ilert navigation menu
{% endstep %}

{% step %}
Open the agent detail view for the agent you want to configure
{% endstep %}

{% step %}
Go to the **Tools** tab
{% endstep %}

{% step %}
Under the **External MCP Servers** section, locate the **AWS MCP Server** row
{% endstep %}

{% step %}
Click **Connect**
{% endstep %}

{% step %}
In the dialog, choose the AWS connector you created under **Select connector** (or create one here — the same Region / Access key / Secret key fields appear)
{% endstep %}

{% step %}
Click **Add**
{% endstep %}

{% step %}
Expand the server card to load its tools and enable the ones the agent may use, then save the agent
{% endstep %}
{% endstepper %}

The AWS integration is now connected and ready to use for root cause analysis.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ilert.com/ai-and-agents/mcp/external/aws.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.