An astronaut overseeing a futuristic data hub

Connect Cognito User Pool Calculator to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Plan your AWS authentication architecture without hitting service limits.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through AWS Cognito.

  1. 01

    Calculate pool capacity

    This capability determines how many resources fit in a single Cognito user pool. It checks if your user, app client, or identity provider counts are within limits.

  2. 02

    Calculate resource usage

    This capability monitors your custom attributes and Lambda triggers. It ensures you stay within the specific resource constraints set by AWS.

  3. 03

    Estimate security profile

    This capability calculates the data footprint and security configuration of your authentication flow. It helps you predict JWT token sizes and validate password policies.

  4. 04

    Estimate SMS throughput

    This capability predicts your daily messaging limits. Use it to see if your configured user base will exceed SMS delivery quotas.

Real work

What teams actually run

01

Scaling User Bases

Determine if your current user pool can handle a projected increase to millions of users.

02

JWT Optimization

Calculate the exact size of ID, access, and refresh tokens to manage network overhead.

03

Attribute Management

Verify that your planned custom attribute schema stays under the 50-attribute limit.

04

SMS Budgeting

Predict daily messaging limits to avoid hitting SMS throughput caps.

One connector, every AI

AWS Cognito works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put AWS Cognito to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

923ms average. Fast in production.

AWS Cognito is checked daily against the live service.

Daily averagePeak 1051ms
Oct 3Today
Fastest day
687ms
Slowest day
1051ms
14-day trend
Improving-20%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of AWS Cognito, so you can see the experience inside your AI.

It does not authenticate your account with AWS Cognito. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

AWS Cognito Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_UxqjWew3NlkEaZt4T8qmHquRQsKoCJZ9NfFxR0I6/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — AWS Cognito capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "cognito-user-pool-calculator-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_UxqjWew3NlkEaZt4T8qmHquRQsKoCJZ9NfFxR0I6/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up AWS Cognito in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AWS Cognito owners hand off.

Cloud architects and backend engineers who need to validate AWS configurations before deployment.

  • 01

    Cloud Architect

    Uses the MCP to design scalable authentication structures that won't hit service ceilings.

  • 02

    Backend Engineer

    Uses the MCP to check if custom attributes or Lambda triggers will cause deployment failures.

  • 03

    DevOps Engineer

    Uses the MCP to forecast SMS throughput and messaging costs.

FAQ

Questions AWS Cognito owners ask.

  • 01

    How do I use this MCP with Claude?

    You connect to the MCP through the Vinkius platform. Once connected, your agent in Claude can immediately call the calculation capabilities.

  • 02

    Can this MCP help with JWT token sizes?

    Yes. The estimate_security_profile capability calculates the data footprint of your authentication flow, including ID, access, and refresh tokens.

  • 03

    What is the limit for custom attributes in Cognito?

    The limit is 50 custom attributes. You can use the calculate_resource_usage capability to check if your plan stays within this limit.

  • 04

    Does this MCP require an AWS connection?

    No. This MCP performs deterministic calculations based on the data you provide to your agent. It does not need direct access to your AWS account.

  • 05

    How many users can fit in one Cognito user pool?

    While limits vary, the capability can calculate if your specific user and app client counts fit within recommended architectural limits.

  • 06

    How many users can I fit in one Cognito pool?

    While there is no hard limit, it is recommended to keep a single pool under 1 million users for optimal performance. You can use calculate_pool_capacity to see if you need to split your users into multiple pools.

  • 07

    Can I check my custom attribute limits?

    Yes, use calculate_resource_usage to verify if your custom attribute count is within the 50-attribute limit and if your standard attributes are within the 20-attribute limit.

  • 08

    How do I estimate SMS costs and limits?

    You can use estimate_sms_throughput to calculate the theoretical maximum daily SMS messages for your user base and check if you will exceed the account-wide limit of 10,000 messages per day.

Connect AWS Cognito to Claude, Cursor, ChatGPT & more