---
title: "Kiwi for AWS"
description: "Have the agent on a Kiwi step call AWS APIs under the IAM permissions it signs in with and read the AWS documentation, through the AWS MCP Server."
canonical: "https://kiwiflow.io/integrations/aws"
---

# Kiwi for AWS

Have the agent on a Kiwi step call AWS APIs under the IAM permissions it signs in with and read the AWS documentation, through the AWS MCP Server.

- Your agent works in AWS through its own connection. Kiwi does not call AWS and never holds its credentials.
- A workflow skill can list AWS among the tools it requires. When you supply your agent's available tools to a skill check and AWS is not among them, the check reports `SK15-UNSUPPORTED-TOOL`.
- A project Admin can add links to AWS, with notes, under Connections and bind them to the steps that use them. The agent reads them with `list_connections`.
- The agent can report the tools and plugins it ran with, including its AWS connection, with `report_configuration`.
- The agent submits links to its work in AWS as the step's outputs. People review them, and sign-off stays with the people your workflow names.

## What your agent can do in AWS

- Call any of more than 15,000 AWS API operations, limited by the IAM permissions of the signed-in identity.
- Search and read the AWS documentation.
- Run a Python script in a sandbox without network access that uses the same IAM permissions.
- Review the server's calls afterwards in AWS CloudTrail.

## Set up

### 1. Connect your agent to Kiwi

Add Kiwi's hosted MCP server, `https://kiwiflow.io/mcp`, to your coding agent.

- [Coding agents](https://kiwiflow.io/integrations#agent)
- [Quickstart](https://docs.kiwiflow.io/quickstart#connect-your-agent)

### 2. Connect your agent to AWS

Add the AWS MCP server to your agent with this URL. The credentials stay with your agent.

```
https://aws-mcp.us-east-1.api.aws/mcp
```

- [AWS documentation](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/getting-started-aws-mcp-server.html)

### 3. Example skill

Publish instructions like these as a workflow skill that lists AWS among its required tools.

```
Read the AWS account, region and stack name from the step's inputs.
Sign in with a read-only IAM role and describe the stack's resources and
its recent events in AWS.
Record the resource ARNs and any failed events in the step's outputs.
Changes to production resources need the run's Owner.
If a call is denied, report a blocker rather than asking for wider access.
```

## More deployment and hosting integrations

- [Kiwi for Microsoft Azure](https://kiwiflow.io/integrations/microsoft-azure.md): Have the agent on a Kiwi step check a Microsoft Azure App Service app and query Azure Monitor, through the Azure MCP Server.
- [Kiwi for Cloudflare](https://kiwiflow.io/integrations/cloudflare.md): Have the agent on a Kiwi step read and change Workers, DNS records and other Cloudflare settings, through the Cloudflare API MCP server.
- [Kiwi for Google Cloud](https://kiwiflow.io/integrations/google-cloud.md): Have the agent on a Kiwi step deploy a container to Cloud Run and read the service back, through Google Cloud's remote MCP server for Cloud Run.
- [Kiwi for Vercel](https://kiwiflow.io/integrations/vercel.md): Have the agent on a Kiwi step check a Vercel preview deployment and read its runtime logs, through Vercel's MCP server.
- [Kiwi for DigitalOcean](https://kiwiflow.io/integrations/digitalocean.md): Have the agent on a Kiwi step update a DigitalOcean App Platform app and follow its deployment, through DigitalOcean's MCP server.
- [Kiwi for Supabase](https://kiwiflow.io/integrations/supabase.md): Have the agent on a Kiwi step apply a database migration to a Supabase project and run the advisors afterwards, through Supabase's MCP server.
- [Kiwi for Netlify](https://kiwiflow.io/integrations/netlify.md): Have the agent on a Kiwi step deploy a site to Netlify and set its environment variables, through Netlify's MCP server.
- [Kiwi for Heroku](https://kiwiflow.io/integrations/heroku.md): Have the agent on a Kiwi step check a Heroku app's dynos, logs and Postgres database, through Heroku's MCP server.
- [Kiwi for Fly.io](https://kiwiflow.io/integrations/fly-io.md): Have the agent on a Kiwi step check a Fly.io app's status, Machines and logs, through the MCP server in Fly.io's flyctl CLI.
- [Kiwi for Render](https://kiwiflow.io/integrations/render.md): Have the agent on a Kiwi step trigger a Render deploy, filter the service's logs and read its metrics, through Render's MCP server.
- [Kiwi for Railway](https://kiwiflow.io/integrations/railway.md): Have the agent on a Kiwi step redeploy a Railway service in a non-production environment, through Railway's MCP server.

- [Get started](https://kiwiflow.io/get-started)
- [Read the setup guide](https://docs.kiwiflow.io/other-tools)