Skip to main content

Amazon SNS / SQS MCP Server

A Model Context Protocol (MCP) server for Amazon SNS / SQS that enables generative AI models to manage SNS Topics and SQS Queues through MCP tools.

Features

This MCP server acts as a bridge between MCP clients and Amazon SNS / SQS, allowing generative AI models to create, configure, and manage Topics / Queues. The server provides a secure way to interact with Amazon SNS / SQS resources while maintaining proper access controls and resource tagging.

graph LR
    A[Model] <--> B[MCP Client]
    B <--> C["Amazon SNS / SQS MCP Server"]
    C <--> D[Amazon SNS / SQS Service]
    style A fill:#f9f,stroke:#333,stroke-width:2px
    style B fill:#bbf,stroke:#333,stroke-width:2px
    style C fill:#bfb,stroke:#333,stroke-width:4px
    style D fill:#fbb,stroke:#333,stroke-width:2px

From a security perspective, this server implements resource tagging to ensure that only resources created through the MCP server can be modified by it. This prevents unauthorized modifications to existing Amazon SNS/SQS resources that were not created by the MCP server.

Key Capabilities

This MCP server provides tools to:

  • Create, list, and manage Amazon SNS topics
  • Create, list, and manage Amazon SNS subscriptions
  • Create, list, and manage Amazon SQS queues
  • Send and receive messages using SNS and SQS

Prerequisites

  1. Install uv from Astral or the GitHub README
  2. Install Python using uv python install 3.10
  3. AWS account with permissions to create and manage Amazon SNS / SQS resources

Setup

IAM Configuration

The authorization between the MCP server and your AWS accounts are performed with AWS profile you setup on the host. There are several ways to setup a AWS profile, however we recommend creating a new IAM role that has AmazonSQSReadOnlyAccess and AmazonSNSReadOnlyAccess permission following the principle of "least privilege". Note, if you want to use tools that mutate your tagged resources, you need to grant AmazonSNSFullAccess and AmazonSQSFullAccess. Finally, configure a AWS profile on the host that assumes the new role (for more information, check out the AWS CLI help page).

Installation

Kiro Cursor VS Code
Add to Kiro Install MCP Server Install on VS Code

Configure the MCP server in your MCP client configuration (e.g., for Kiro, edit ~/.kiro/settings/mcp.json):

{
  "mcpServers": {
    "awslabs.amazon-sns-sqs-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.amazon-sns-sqs-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Windows Installation

For Windows users, the MCP server configuration format is slightly different:

{
  "mcpServers": {
    "awslabs.amazon-sns-sqs-mcp-server": {
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "awslabs.amazon-sns-sqs-mcp-server@latest",
        "awslabs.amazon-sns-sqs-mcp-server.exe"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

or docker after a successful docker build -t awslabs/amazon-sns-sqs-mcp-server.:

# fictitious `.env` file with AWS temporary credentials
AWS_ACCESS_KEY_ID=<from the profile you set up>
AWS_SECRET_ACCESS_KEY=<from the profile you set up>
AWS_SESSION_TOKEN=<from the profile you set up>
  {
    "mcpServers": {
      "awslabs.sns-sqs-mcp-server": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "--interactive",
          "--env-file",
          "/full/path/to/file/above/.env",
          "awslabs/amazon-sns-sqs-mcp-server:latest"
        ],
        "env": {},
        "disabled": false,
        "autoApprove": []
      }
    }
  }

Server Configuration Options

The Amazon SNS / SQS MCP Server supports several command-line arguments that can be used to configure its behavior:

--allow-resource-creation

Enables tools that create resources in the user's AWS account. When this flag is not enabled, the create new resources tools will be hidden from the MCP client, preventing the creation of new Amazon SNS / SQS resources. It also currently prevents deletion of any topics / queues. Default is False.

This flag is particularly useful for:

  • Testing environments where resource creation should be restricted
  • Limiting the scope of actions available to the AI model

Example:

uv run awslabs.amazon-sns-sqs-mcp-server --disallow-resource-creation

Security Features

The MCP server implements a security mechanism that only allows modification of resources that were created by the MCP server itself. This is achieved by:

  1. Automatically tagging all created resources with a mcp_server_version tag
  2. Validating this tag before allowing any mutative actions (update, delete) - this is a deterministic check that ensures only resources created by the MCP server can be modified
  3. Rejecting operations on resources that don't have the appropriate tag
  4. Application-to-Person (A2P) messaging mutative operations are not enabled by default for security reasons

Best Practices

  • Use descriptive topic and queue names to easily identify resources
  • Follow the principle of least privilege when setting up IAM permissions
  • Use separate AWS profiles for different environments (dev, test, prod)
  • Implement proper error handling in your client applications

Security Considerations

When using this MCP server, consider:

  • The MCP server needs permissions to create and manage Amazon SNS / SQS resources
  • Only resources created by the MCP server can be modified by it since they are tagged
  • Resource creation is disabled by default, enable it by setting the --allow-resource-creation flag on

Troubleshooting

  • If you encounter permission errors, verify your IAM user has the correct policies attached
  • For connection issues, check network configurations and security groups
  • If resource modification fails with a tag validation error, it means the resource was not created by the MCP server
  • For general Amazon SNS / SQS issues, consult the Amazon SNS documentation , Amazon SQS documentation

Version

Current MCP server version: 1.0.0

Release files for awslabs.amazon-sns-sqs-mcp-server 2.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for awslabs.amazon-sns-sqs-mcp-server 2.1.1
File Size Uploaded
awslabs_amazon_sns_sqs_mcp_server-2.1.1.tar.gz 121.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for awslabs.amazon-sns-sqs-mcp-server 2.1.1
File Interpreter ABI Platform
awslabs_amazon_sns_sqs_mcp_server-2.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 143.0 kB

Release files / awslabs_amazon_sns_sqs_mcp_server-2.1.1.tar.gz

Download URL awslabs_amazon_sns_sqs_mcp_server-2.1.1.tar.gz
Size 121.9 kB
Tags Source
SHA-256 checksum
How to use checksums
625d825b752de966e9f118b7f59f4230f4be4eec119e7fef769acdb6d7ef6ffb
BLAKE2b-256 checksum
How to use checksums
f72e5aee91c7b345037ed91864b4a38b4d45f9e6a6613f90b000a4d52212c247
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 8, 2026.

Transparency log

Release files / awslabs_amazon_sns_sqs_mcp_server-2.1.1-py3-none-any.whl

Download URL awslabs_amazon_sns_sqs_mcp_server-2.1.1-py3-none-any.whl
Size 21.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
2e0b8f368ee892fb20a2784d4c4f46c577672c30b933911aa469b7da58744f5f
BLAKE2b-256 checksum
How to use checksums
fa70cee49724747590a1c141e6cc1c6486a1467d6acfecd655ae7207f034bf70
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 8, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

2.1.1 This release

2 release files

2.1.0

2 release files

2.0.23

2 release files

2.0.21

2 release files

2.0.18

2 release files

2.0.14

2 release files

2.0.12

2 release files

2.0.11

2 release files

2.0.10

2 release files

2.0.9

2 release files

2.0.8

2 release files

2.0.7

2 release files

2.0.5

2 release files

2.0.4

2 release files

2.0.3

2 release files

2.0.2

2 release files

2.0.1

2 release files

2.0.0

2 release files

1.0.3

2 release files

1.0.2

2 release files

1.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page