Does this MCP handle all AWS CodeBuild limits?

It validates buildspec size, timeouts, and resource limits against known AWS hard limits. It's designed to give you a complete picture of what's possible within the CodeBuild environment.

What if my buildspec is too large?

The calculate_project_constraints capability will tell you immediately if your buildspec size exceeds the hard limit, and it will explain why the build will fail.

How do I find the right compute type?

You use the calculate_compute_and_config capability. You input your memory requirements, and it maps that to a specific compute type, like BUILD_GENERAL1_LARGE, and handles VPC configuration.

Is this only for AWS users?

No. This MCP is specifically designed for AWS CodeBuild, so it uses AWS standards to calculate the required resource sizing and constraints for your pipelines.

How do I know if my buildspec is too large?

You can use the calculate_project_constraints capability. It will check your buildspec size against the 64 KB hard limit and flag it if it exceeds the allowed value.

Can I run Docker builds with this capability?

Yes. By using calculate_compute_and_config, you can specify if your build requires Docker. The capability will then determine if privileged mode is required for your configuration.

What are the concurrency limits for Linux builds?

The calculate_resource_sizing capability will recommend a concurrency limit of 60 for Linux-based environments.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Aws Codebuild Project Sizing 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. Stop build failures before they start.

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 AWS CodeBuild.

01
Calculate project constraints
Validates the buildspec and timeout against AWS hard limits
02
Calculate compute and config
Maps resource requirements to specific AWS CodeBuild compute types and network configurations
03
Calculate resource sizing
Determines recommended storage, concurrency, and variable limits

Real work

What teams actually run

Migrating an existing pipeline

You're moving a legacy CodeBuild project. Use the MCP to check if the current resource settings will pass AWS limits.

Designing a new microservice

Before writing a single line of code, use the MCP to determine the minimum required compute type and storage capacity.

Scaling up a critical service

When increasing concurrency, the MCP calculates the necessary resource and variable limits to support the higher load.

Debugging build failures

If a build fails mysteriously, run the MCP to validate the buildspec and pinpoint if the failure is due to a hard limit violation.

One connector, every AI

AWS CodeBuild 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 CodeBuild 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

932ms average. Fast in production.

AWS CodeBuild is checked daily against the live service.

Daily averagePeak 1205ms

Oct 3Today

Fastest day: 652ms
Slowest day: 1205ms
14-day trend: Stable+2%

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 AWS CodeBuild, so you can see the experience inside your AI.

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

AWS CodeBuild Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_ViwwoZVDXE2fhXkFg1zp7VIbRekc4L8WxIb90mtd/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 — AWS CodeBuild capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "aws-codebuild-project-sizing-calculator-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ViwwoZVDXE2fhXkFg1zp7VIbRekc4L8WxIb90mtd/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 CodeBuild in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AWS CodeBuild owners hand off.

This MCP is essential for DevOps Engineers, Site Reliability Engineers, and DevOps Architects. If your job involves setting up, testing, or scaling CI/CD pipelines on AWS, you need this. It takes the guesswork out of infrastructure sizing, letting you focus on the code, not the constraints.

01
DevOps Engineer
Uses the MCP to validate buildspecs and ensure CI/CD pipelines adhere to AWS resource limits.
02
Site Reliability Engineer (SRE)
Relies on the MCP to calculate optimal compute types and resource sizing for mission-critical deployments.
03
Cloud Architect
Uses the MCP to map memory requirements to specific AWS compute types and configure VPC settings accurately.

FAQ

Questions AWS CodeBuild owners ask.

01
Does this MCP handle all AWS CodeBuild limits?
It validates buildspec size, timeouts, and resource limits against known AWS hard limits. It's designed to give you a complete picture of what's possible within the CodeBuild environment.
02
What if my buildspec is too large?
The calculate_project_constraints capability will tell you immediately if your buildspec size exceeds the hard limit, and it will explain why the build will fail.
03
How do I find the right compute type?
You use the calculate_compute_and_config capability. You input your memory requirements, and it maps that to a specific compute type, like BUILD_GENERAL1_LARGE, and handles VPC configuration.
04
Is this only for AWS users?
No. This MCP is specifically designed for AWS CodeBuild, so it uses AWS standards to calculate the required resource sizing and constraints for your pipelines.
05
How do I know if my buildspec is too large?
You can use the calculate_project_constraints capability. It will check your buildspec size against the 64 KB hard limit and flag it if it exceeds the allowed value.
06
Can I run Docker builds with this capability?
Yes. By using calculate_compute_and_config, you can specify if your build requires Docker. The capability will then determine if privileged mode is required for your configuration.
07
What are the concurrency limits for Linux builds?
The calculate_resource_sizing capability will recommend a concurrency limit of 60 for Linux-based environments.

Explore

More in Devops

Connect AWS CodeBuild 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

Calculate project constraints

Calculate compute and config

Calculate resource sizing

What teams actually run

Migrating an existing pipeline

Designing a new microservice

Scaling up a critical service

Debugging build failures

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

AWS CodeBuild Connector

Claude Desktop

DevOps Engineer

Site Reliability Engineer (SRE)

Cloud Architect

Does this MCP handle all AWS CodeBuild limits?

What if my buildspec is too large?

How do I find the right compute type?

Is this only for AWS users?

How do I know if my buildspec is too large?

Can I run Docker builds with this capability?

What are the concurrency limits for Linux builds?

AWS Config Coverage Calculator AI Connector

AWS SSM Parameter Store Sizing Calculator AI Connector

AWS Neptune Sizing Calculator AI Connector

AWS Timestream Sizing Calculator AI Connector

Suggestions

Infrastructure Project Finance Viability AI Connector

AWS Redshift Cluster Calculator AI Connector

AWS App Runner Scaling Calculator AI Connector

AWS MSK Partition & Throughput Calculator AI Connector