Skip to content
MCP server

Khavion Architecture Review

Quote cloud providers' own best practices and review Terraform and Kubernetes files

Runs locallyStatus and history
Install
Pricing
Free
Platforms
CLI, API
Runs
Locally
Version
0.1.1
Listing updated
3 days ago

About Khavion Architecture Review

Khavion Architecture Review is a free MCP server for cloud and infrastructure. It runs locally on your machine and is started by your AI client.

Nothing in this server calls an AI model. Findings come from a fixed, version-controlled rule set, so the same input always yields the same output, and citation lookups return the provider's own sentence quoted word for word with a link to the page it came from.

It runs locally over stdio on Node 20 or later and reads files on your machine. The site says the only things that leave it are your key, rule ids and one number, the count of services found, and only when a key is used. No file contents are sent.

Without a key, lookups are complete but a review shows the top three findings. A free key from a work email unlocks every finding, an estimated quote total, a recommended next step and a link to the full report; the price lines are estimates, not offers. The same engine also ships as a command line tool and a GitHub Action that comments on pull requests.

Install

Run in a terminal

claude mcp add architecture-review-mcp --env KHAVION_API_KEY='<KHAVION_API_KEY>' -- npx -y @khavion/architecture-review-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "architecture-review-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@khavion/architecture-review-mcp"
      ],
      "env": {
        "KHAVION_API_KEY": "<KHAVION_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "architecture-review-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@khavion/architecture-review-mcp"
      ],
      "env": {
        "KHAVION_API_KEY": "<KHAVION_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "architecture-review-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@khavion/architecture-review-mcp"
      ],
      "env": {
        "KHAVION_API_KEY": "<KHAVION_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "architecture-review-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@khavion/architecture-review-mcp"
      ],
      "env": {
        "KHAVION_API_KEY": "<KHAVION_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "architecture-review-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@khavion/architecture-review-mcp"
      ],
      "env": {
        "KHAVION_API_KEY": "<KHAVION_API_KEY>"
      }
    }
  }
}

Configuration

  • KHAVION_API_KEYOptional. A free Khavion work-email API key (https://khavion.com/tools/api-key). Without it, reviews show the top 3 findings.

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

lookup_citation
Returns up to five cited rules for a service, pillar and question.
review_iac
Reviews Terraform, CloudFormation or Kubernetes file contents.
review_stack
Reviews a list of services with an optional workload description.
explain_finding
Explains one finding with why it matters, the fix and the citation.

What it does

Verbatim citations
Returns up to five cited rules for a service, each with a quote and its source page.
Infrastructure review
Reviews Terraform, CloudFormation or Kubernetes files you point it at.
Stack review
Reviews a list of named services with an optional workload description.
Finding explanations
Explains why a finding matters, the fix and its citation.
Deterministic rules
Fixed rule set, no model and no file contents sent.

Good for

  • Check a Terraform change before a pull request
  • Get the provider's own wording for a design question
  • Sanity-check a proposed list of cloud services
  • Comment top findings on PRs through the GitHub Action

Pricing

Free

Free; a free work-email key unlocks full reviews

Prices change. Check khavion.com before you buy.

Khavion Architecture Review FAQ

Is it free?

Yes. A free key from a work email shows full reviews.

What does it send off my machine?

Only your key, rule ids and a service count, and only when a key is used.

What runs it?

Node 20 or later via npx -y @khavion/architecture-review-mcp.

What is limited without a key?

Reviews show the top three findings; citation lookup stays complete.

Is Khavion Architecture Review free?

Yes. Khavion Architecture Review is free to use.

How do I add Khavion Architecture Review to Claude Code?

Run this command in your terminal: claude mcp add architecture-review-mcp --env KHAVION_API_KEY='<KHAVION_API_KEY>' -- npx -y @khavion/architecture-review-mcp

What are the best alternatives to Khavion Architecture Review?

The closest alternatives to Khavion Architecture Review are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Khavion Architecture Review

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools