Cloudwright runs on your own machine — the client starts it, so there is no endpoint to ping. 179 installs a week from pypi. Last commit 24 Aug 2026.
Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC.
We read the source, 2 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
proc = subprocess.run(
…f(S.state===cl)return Eh(u);S.state===bh?(S.state=ul,S.timer.stop(),S.on.call("interrupt",t,t.__data__,S.index,S.group),delete l[v]):+v<r&&(S.state=ul,S.timer.stop(),S.on.call("cancel",t,t.__data__,S.index,S.group),delete l[v])}if(Eh(function(){i.state===cl&&(i.state=bh,i.timer.r…
typer.Option("--profile", help="AWS named profile (~/.aws/credentials)"),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Cloudwright every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cloudwright -- uvx cloudwright-ai-mcp
{
"mcpServers": {
"cloudwright": {
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}
[mcp_servers.cloudwright]
command = "uvx"
args = ["cloudwright-ai-mcp"]
{
"mcpServers": {
"cloudwright": {
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}
{
"servers": {
"cloudwright": {
"type": "stdio",
"command": "uvx",
"args": [
"cloudwright-ai-mcp"
]
}
}
}
Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud
Draw cloud architecture diagrams with official AWS, Azure and GCP icons from a prompt or Terraform.
Architecture graphs from Terraform, CDK, CloudFormation, Pulumi and ARM, for coding agents
European cloud hosting. Deploy and manage apps with your favorite AI coding assistant.
Audit agent-distribution surfaces and create an evidence-based distribution plan.
Simulate cloud infrastructure and estimate cost before deploying or changing infrastructure.
Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Control Plane (controlplane.com): deploy and operate workloads across AWS, GCP, Azure, and more.
Answers built from our own checks of this server.