AWS Cognito MCP Server Integration

What does “AWS Cognito” MCP Server do?

The AWS Cognito MCP Server is a Model Context Protocol (MCP) server implementation that integrates with Amazon Cognito to provide authentication and user management capabilities for AI assistants and development tools. By acting as a bridge between AI clients and AWS Cognito, it allows secure user authentication workflows such as sign-up, sign-in, password reset, and multi-factor authentication directly from environments like Claude or other MCP-compatible clients. This enables developers to manage user identities, sessions, and security features programmatically, streamlining the process of integrating robust authentication into apps, bots, or automated workflows while maintaining security through AWS infrastructure.

List of Prompts

No prompt templates are mentioned or described in the repository or documentation.

List of Resources

No explicit MCP resources are listed or described in the repository or documentation.

List of Tools

• sign_up: Register a new user using an email and password.
• sign_up_confirm_code_from_email: Verify a new account with a confirmation code sent via email.
• sign_in: Authenticate a user with username and password.
• sign_out: Sign out the current user.
• getCurrentUser: Retrieve details of the current signed-in user.
• reset_password_send_code: Request a password reset code for a user.
• reset_password_veryify_code: Reset a password using a verification code.
• change_password: Change the password for the currently signed-in user.
• refresh_session: Refresh authentication tokens for the user session.
• update_user_attributes: Update user profile attributes such as name or email.
• delete_user: Delete the currently signed-in user account.
• resend_confirmation_code: Resend an account verification code.
• verify_software_token: Verify a Time-based One-Time Password (TOTP) code for multi-factor authentication (MFA).

Use Cases of this MCP Server

• User Registration Automation: Easily script and automate user sign-up flows, including email confirmation and attribute setup, for onboarding workflows in apps and services.
• Secure User Sign-In for Bots/Agents: Allow AI assistants to securely log in and maintain authenticated sessions for personalized or restricted actions.
• Password Management Workflows: Enable automated handling of password resets, code delivery, and password changes for self-service user support.
• Multi-Factor Authentication Integration: Add TOTP-based MFA to flows managed by AI agents, enhancing security for sensitive operations.
• User Lifecycle Management: Programmatically update user attributes, refresh sessions, or delete users as part of automated administrative or customer support processes.

How to set it up

Windsurf

No setup instructions for Windsurf are provided in the documentation.

Claude

1. Ensure Node.js 18 or higher is installed on your system.
2. Go to: Settings > Developer > Edit Config in Claude Desktop.
3. Add the following to your claude_desktop_config.json:

   {
     "mcpServers": {
       "aws-cognito-mcp-server": {
         "command": "/path/to/mcp-server-aws-cognito/build/index.js",
         "env": {
           "AWS_COGNITO_USER_POOL_ID": "your-user-pool-id",
           "AWS_COGNITO_USER_POOL_CLIENT_ID": "your-app-client-id"
         }
       }
     }
   }
   

4. Save and restart Claude.
5. Verify the server is available in the MCP servers list.

Securing API Keys: Place your AWS Cognito credentials in the env section as shown above. Do not hard-code sensitive information.

Cursor

No setup instructions for Cursor are provided in the documentation.

Cline

No setup instructions for Cline are provided in the documentation.

Claude Code

1. Ensure Node.js 18+ is installed.
2. Install Claude Code using the instructions at Claude Code Documentation.
3. Add the AWS Cognito MCP Server:

   claude mcp add "aws-cognito-mcp" npx tsx index.ts
   

4. Verify it’s been added:

   claude mcp list
   

5. Run Claude with your MCP server:

   claude
   

Securing API Keys: Use a .env file or set environment variables for AWS_COGNITO_USER_POOL_ID and AWS_COGNITO_USER_POOL_CLIENT_ID.

Example .env:

AWS_COGNITO_USER_POOL_ID=your-user-pool-id
AWS_COGNITO_USER_POOL_CLIENT_ID=your-app-client-id

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "aws-cognito-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “aws-cognito-mcp-server” to the actual name of your MCP server and replace the URL with your own MCP server URL.

Overview

Our opinion

The AWS Cognito MCP Server provides a robust set of authentication tools and is well-documented for use with Claude and Claude Code, but lacks prompt templates and explicit MCP resources. The server would benefit from more examples, resource definitions, and clarity on Roots and Sampling support. As it stands, it is a solid integration for AWS Cognito authentication in AI workflows, but somewhat limited in broader MCP feature usage.

MCP Score

Rating: 5/10 — Good tool coverage for authentication, but missing resources, prompts, explicit sampling/roots support, and a LICENSE. Room for improvement in MCP completeness and open-source readiness.