FRENES

Cloud platforms · MCP server

Cloudwright: MCP server, setup and security

Cloudwright is an open-source MCP server that lets an AI agent design cloud architectures and estimate costs, compliance and potential impact. Its repository has 33 stars and its last commit is from August 24, 2026 and it is licensed under MIT.

Actively maintained

What Cloudwright does

According to its repository: “Cloud architecture design for AWS, GCP, Azure and Databricks: cost estimates, compliance checks, Terraform/CloudFormation export and blast-radius analysis.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Cloudwright is listed under Cloud platforms, a category of 116 servers in the directory, where it ranks #64 by stars.

Topics declared by the repository: aws, azure, cli, cloud-architecture, cloud-design, cost-estimation.

Installing and connecting Cloudwright

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Cloudwright. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 28, 2026, the xmpuspus/cloudwright repository has 33 stars and 2 forks, with 0 open issues. It has more stars than 46% of the servers in the directory. Last change 2 months ago. Version published in the registry: 1.10.0 (August 24, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

CoderCoder : 17.2K17.2KKubesharkKubeshark : 12.1K12.1KAwslabs MCPAwslabs MCP : 9.8K9.8KMCP server cloudflareMCP server cloudflare : 4.4K4.4KKubefwdKubefwd : 4.2K4.2KSocraticodeSocraticode : 3.4K3.4KKubernetes MCP serverKubernetes MCP server : 2.2K2.2KAzure DevOps (ADO)Azure DevOps (ADO) : 2.1K2.1KCloudwrightCloudwright : 3333
GitHub stars of the most followed servers in the category (log scale); Cloudwright in orange. Checked October 25, 2026.

Verdict

Cloudwright is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Frequently asked questions

How do I install Cloudwright?

Cloudwright is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of xmpuspus/cloudwright.

Is Cloudwright free?

The code is published under the MIT licence and can be used free of charge.

Is Cloudwright safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by xmpuspus on GitHub. Check who maintains it before giving it access.

What are the alternatives to Cloudwright?

In the same category: MCP server cloudflare, Awslabs MCP, Terraform, and Kubefwd. MCP server cloudflare and Awslabs MCP score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score