# AWS MCP server

> Call AWS APIs, run sandboxed Python scripts and search AWS documentation and skills from a managed AWS-hosted server.

- Listing: https://mcp.tc/i/aws-mcp
- Connect: use the server's own URL `https://aws-mcp.us-east-1.api.aws/mcp` (sign-in optional); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: optional (works without sign-in)
- Category: [Cloud & DevOps](https://mcp.tc/c/cloud-devops)
- Vendor: Amazon Web Services
- Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe.
- Homepage: <https://docs.aws.amazon.com/agent-toolkit/latest/userguide/getting-started-aws-mcp-server.html>
- Docs: <https://github.com/aws/mcp-proxy-for-aws/blob/main/README.md>
- Repository: <https://github.com/aws/mcp-proxy-for-aws>
- Package: pypi `mcp-proxy-for-aws`

## About

A managed MCP server from AWS that gives an assistant access to AWS. It can run Python scripts in a sandbox that calls AWS APIs through boto3, generate pre-signed S3 URLs, search and read AWS documentation, retrieve AWS skills, and look up regions and regional service availability.

It runs as a hosted streamable HTTP endpoint at aws-mcp.us-east-1.api.aws. Documentation, region and availability tools work without sign-in. Running scripts and acting on an account need AWS sign-in through OAuth, or SigV4 signing with local AWS credentials through the mcp-proxy-for-aws package, which requires Python and uv.

## What it can do

- Run sandboxed Python that calls AWS APIs via boto3
- Generate pre-signed S3 upload and download URLs
- Search and read AWS documentation
- Retrieve AWS skills and workflow guides
- List AWS regions
- Check service, API and CloudFormation availability by region
- Poll long-running tasks

## Tools (8)

- `aws___get_presigned_url`: Generate pre-signed S3 URLs for uploading or downloading files.
- `aws___get_tasks`: Poll the status of long-running tasks by task ID. (read-only)
- `aws___run_script`: Run Python in a sandbox with AWS API access through call\_boto3. (can modify or delete data)
- `aws___get_regional_availability`: Check whether AWS products, APIs or CloudFormation resources are available per region. (read-only)
- `aws___list_regions`: Retrieve a list of all AWS regions. (read-only)
- `aws___read_documentation`: Fetch full AWS documentation pages as markdown. (read-only)
- `aws___retrieve_skill`: Retrieve an AWS skill's SKILL.md or a referenced file. (read-only)
- `aws___search_documentation`: Search AWS documentation by topic and return page text chunks. (read-only)

## Example prompts

- "List all S3 buckets in my AWS account and show their regions"
- "Search AWS docs for how to configure a Lambda function URL"
- "Is Amazon Bedrock available in eu-central-1 and ap-southeast-2?"
- "Give me a pre-signed URL to upload a file to my S3 bucket"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http aws-mcp https://aws-mcp.us-east-1.api.aws/mcp
```

2. Start Claude Code and type `/mcp`. **aws-mcp** should show as connected. To sign in for more access, pick it and choose **Authenticate**.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **AWS** and paste this URL:

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

3. Click **Add**, then **Connect**. Signing in to Amazon Web Services is optional.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=AWS&connectorUrl=https%3A%2F%2Faws-mcp.us-east-1.api.aws%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://aws-mcp.us-east-1.api.aws/mcp` and click **Add**.

3. Click **Connect**. Signing in to Amazon Web Services is optional.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://aws-mcp.us-east-1.api.aws/mcp` as the server URL and choose **No authentication**, or **OAuth** to sign in to Amazon Web Services for more access.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=aws-mcp&config=eyJ1cmwiOiJodHRwczovL2F3cy1tY3AudXMtZWFzdC0xLmFwaS5hd3MvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "aws-mcp": {
      "url": "https://aws-mcp.us-east-1.api.aws/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=aws-mcp&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Faws-mcp.us-east-1.api.aws%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"aws-mcp","type":"http","url":"https://aws-mcp.us-east-1.api.aws/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "aws-mcp": {
      "type": "http",
      "url": "https://aws-mcp.us-east-1.api.aws/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "aws-mcp": {
      "serverUrl": "https://aws-mcp.us-east-1.api.aws/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add aws-mcp --url https://aws-mcp.us-east-1.api.aws/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.aws-mcp]
url = "https://aws-mcp.us-east-1.api.aws/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http aws-mcp https://aws-mcp.us-east-1.api.aws/mcp
```

Then, inside Gemini CLI, run `/mcp auth aws-mcp` to sign in (optional).

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "aws-mcp": {
      "type": "http",
      "url": "https://aws-mcp.us-east-1.api.aws/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://aws-mcp.us-east-1.api.aws/mcp`.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-06-18
- Last checked: 2026-10-03 (reachable)
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/aws-mcp (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report