Khavion Architecture Review
NPM · @KHAVION/ARCHITECTURE-REVIEW-MCP
Cited cloud best practices and a rules-based review of Terraform, CloudFormation, and Kubernetes.
Available components
Last scanned (1 day ago)
Scores higher than 31% of npm servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security63
- No malware found by supply-chain analysis.Pass
- Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
- No install/post-install scripts declared.Pass
- Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 470 tokens (~117/item across 4 items; 4 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 60
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/@khavion/architecture-review-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
explain_finding Explain a finding ~77
Explain one finding by rule id (for example aws-sec-encryption-at-rest) or by the 8-character id used in report links. Returns why it matters, the fix, and the verbatim citation with its link. Free and offline.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | A rule id, or an 8-character hexadecimal report id. |
No output schema declared.
No examples provided.
lookup_citation Look up a cited best practice ~148
Find the cloud provider's own documentation for a service. Returns up to 5 rules for the service, each with a verbatim quote from the provider's docs and the page link. Free, offline, and complete. Use it to ground a recommendation in a primary source before you state it.
| Name | Type | Req | Description |
|---|---|---|---|
| pillar | string | – | Limit results to one Well-Architected pillar. Omit to search all pillars. |
| question | string | – | What you want to know, in a sentence. Used only to rank the matches by shared keywords. |
| service | string | yes | The service, by name or id. Examples: S3, Amazon RDS, Lambda, Key Vault, Cloud Run. |
No output schema declared.
No examples provided.
review_iac Review infrastructure as code ~120
Review Terraform, CloudFormation, or Kubernetes files against cited cloud best practices. Pass the file contents. Without an API key it returns the top 3 findings by severity plus counts for the rest. With KHAVION_API_KEY set in the server's environment and valid, it returns every finding, the quote total, the recommended next step, and a report link. File contents stay on this machine; only the key, rule ids, and a count of services are sent to Khavion.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | The infrastructure files to review. |
No output schema declared.
No examples provided.
review_stack Review a list of services ~125
Review a stack described as a list of services, such as s3, rds, lambda. Optionally add a sentence about the workload. Same output rules as review_iac: the top 3 findings without a valid API key, everything with one. Nothing but the key, rule ids, and a count of services leaves this machine.
| Name | Type | Req | Description |
|---|---|---|---|
| intent | string | – | One or two sentences about the workload, for example whether it is public-facing. |
| tokens | array | yes | Service ids or names. Examples: s3, rds, Amazon EC2, Key Vault. |
No output schema declared.
No examples provided.
How do I install the Khavion Architecture Review MCP server?
Khavion Architecture Review runs locally as an npm package, launched with npx -y @khavion/architecture-review-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @khavion/architecture-review-mcp
claude mcp add com-khavion-architecture-review-mcp -- npx -y @khavion/architecture-review-mcp
What is the Khavion Architecture Review MCP server?
Khavion Architecture Review is an MCP server listed in the public MCP registry as com.khavion/architecture-review-mcp. Cited cloud best practices and a rules-based review of Terraform, CloudFormation, and Kubernetes. This page covers its npm package (@khavion/architecture-review-mcp).
Is the Khavion Architecture Review MCP server safe to use?
Khavion Architecture Review scores 60 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Khavion Architecture Review MCP server expose?
Khavion Architecture Review exposes 4 tools: lookup_citation, review_iac, review_stack, explain_finding. Their descriptions and schemas cost roughly 470 tokens of context every time the server is loaded.
Is the Khavion Architecture Review MCP server still maintained?
Khavion Architecture Review is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Khavion Architecture Review MCP server under?
Khavion Architecture Review declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.