How does this MCP calculate resource requests?

It uses historical usage percentiles like p50, p95, or p99 and applies a multiplier to determine the final CPU and memory values.

Can I use this with Claude or Cursor?

Yes, you can connect this MCP to any compatible client like Claude, Cursor, or Windsurf once you connect via Vinkius.

What is a scaling ratio?

It is the ratio between your resource limits and your resource requests. The MCP can validate if this ratio is within safe operational boundaries.

Does this capability help with cluster capacity planning?

Yes, you can use the estimate_cluster_demand capability to project total resource requirements based on pod specs and replica counts.

Do I need to host the MCP myself?

No, Vinkius hosts and manages the MCP for you. You just connect your client and start using the capabilities.

How does the capability calculate CPU and memory requests?

The generate_resource_specification capability looks up the value in your provided metrics (p50, p95, or p99) that matches your chosen strategy percentile and sets that as the request.

What is a 'Guaranteed' QoS class?

A pod is in the Guaranteed class if both its CPU request equals its limit and its memory request equals its limit.

Can I use this to plan for large-scale deployments?

Yes, you can use estimate_cluster_demand to project the total CPU and memory footprint required for any number of replicas.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Kubernetes Resource Request Calculator to your AI

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. Turn historical usage metrics into precise pod specifications.

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.

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.

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 · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Kubernetes Resource Calculator.

01
Estimate cluster demand
This capability calculates the total resource footprint for a deployment. It uses your pod specs and replica counts to project fleet-wide requirements.
02
Validate scaling ratio
Use this capability to check if your limit-to-request ratio stays within safe operational bounds. It identifies if your settings are too aggressive.
03
Generate resource specification
This capability builds a complete resource configuration based on your historical usage data. It outputs specific CPU and memory requests and limits.

Real work

What teams actually run

Right-sizing Pods

You provide p95 usage data and get precise CPU and memory limits for your deployment manifests.

Capacity Planning

You calculate the total CPU and memory needed for a fleet of replicas before you scale out.

Risk Assessment

You check if your current limit-to-request ratios are too high for your specific workload type.

Automated Spec Generation

Your agent creates resource configurations using a specific multiplier to ensure consistent headroom.

One connector, every AI

Kubernetes Resource Calculator 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 Kubernetes Resource Calculator 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

683ms average. Fast in production.

Kubernetes Resource Calculator is checked daily against the live service.

Daily averagePeak 790ms

Oct 3Today

Fastest day: 529ms
Slowest day: 790ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 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 Kubernetes Resource Calculator, so you can see the experience inside your AI.

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

Kubernetes Resource Calculator Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_XwKoTMcUkhyOCkZdcYlfU4k00pRK7eRAzqyUhny3/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Kubernetes Resource Calculator capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "kubernetes-resource-request-calculator-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_XwKoTMcUkhyOCkZdcYlfU4k00pRK7eRAzqyUhny3/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 Kubernetes Resource Calculator in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Kubernetes Resource Calculator owners hand off.

This MCP is built for engineers managing containerized workloads who need to move away from manual resource tuning.

01
DevOps Engineer
Hands off usage metrics to the AI to get production-ready YAML specs.
02
SRE
Uses the capability to validate that scaling ratios won't cause node instability.
03
Platform Engineer
Asks the agent to project total cluster demand for capacity planning.

FAQ

Questions Kubernetes Resource Calculator owners ask.

01
How does this MCP calculate resource requests?
It uses historical usage percentiles like p50, p95, or p99 and applies a multiplier to determine the final CPU and memory values.
02
Can I use this with Claude or Cursor?
Yes, you can connect this MCP to any compatible client like Claude, Cursor, or Windsurf once you connect via Vinkius.
03
What is a scaling ratio?
It is the ratio between your resource limits and your resource requests. The MCP can validate if this ratio is within safe operational boundaries.
04
Does this capability help with cluster capacity planning?
Yes, you can use the estimate_cluster_demand capability to project total resource requirements based on pod specs and replica counts.
05
Do I need to host the MCP myself?
No, Vinkius hosts and manages the MCP for you. You just connect your client and start using the capabilities.
06
How does the capability calculate CPU and memory requests?
The generate_resource_specification capability looks up the value in your provided metrics (p50, p95, or p99) that matches your chosen strategy percentile and sets that as the request.
07
What is a 'Guaranteed' QoS class?
A pod is in the Guaranteed class if both its CPU request equals its limit and its memory request equals its limit.
08
Can I use this to plan for large-scale deployments?
Yes, you can use estimate_cluster_demand to project the total CPU and memory footprint required for any number of replicas.

Explore

More in Infrastructure

Connect Kubernetes Resource Calculator to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Estimate cluster demand

Validate scaling ratio

Generate resource specification

What teams actually run

Right-sizing Pods

Capacity Planning

Risk Assessment

Automated Spec Generation

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

Kubernetes Resource Calculator Connector

Claude Desktop

DevOps Engineer

SRE

Platform Engineer

How does this MCP calculate resource requests?

Can I use this with Claude or Cursor?

What is a scaling ratio?

Does this capability help with cluster capacity planning?

Do I need to host the MCP myself?

How does the capability calculate CPU and memory requests?

What is a 'Guaranteed' QoS class?

Can I use this to plan for large-scale deployments?

AWS Config Coverage Calculator AI Connector

Kubernetes Architecture Prover AI Connector

Resource Limit Calculator AI Connector

AWS Secrets Manager Rotation Calculator AI Connector

Suggestions

Civo (Cloud-native Kubernetes Cloud Provider API) AI Connector

JD Cloud Infrastructure AI Connector

UpCloud AI Connector

Mosaic (Resource Planning & Workforce Management) AI Connector