# Archprint (npm · archprint)

Mine the architecture rules your TypeScript repo already enforces, with the evidence attached.

- Trust score: 83/100 (high trust)
- Change this week: −11
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `archprint`: 83/100 (this document), [markdown](https://verifymcp.io/servers/tommkruix-archprint/archprint.md), [page](https://verifymcp.io/servers/tommkruix-archprint/archprint)

## Channel facts

- Registry: `npm`
- Package: `archprint`
- Version: `0.18.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 63/100
  - No malware found by supply-chain analysis.
  - Known CVEs could not be checked: the version this server declares is not published in its registry.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: the version this server declares is not published in its registry.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Tommkruix/archprint).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1099 tokens (~219/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Archprint MCP server?

Archprint runs locally as an npm package, launched with npx -y archprint mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add tommkruix-archprint -- npx -y archprint mcp
```

### Cursor

```json
{
  "mcpServers": {
    "tommkruix-archprint": {
      "command": "npx",
      "args": [
        "-y",
        "archprint",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tommkruix-archprint": {
      "command": "npx",
      "args": [
        "-y",
        "archprint",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tommkruix-archprint -- npx -y archprint mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tommkruix-archprint": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "archprint",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tommkruix-archprint --command npx --arg -y --arg archprint --arg mcp
```

### Hermes

```yaml
mcp_servers:
  tommkruix-archprint:
    command: "npx"
    args: ["-y", "archprint", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "tommkruix-archprint": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "archprint",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tommkruix-archprint -t stdio -c npx -a -y archprint mcp
```

### Other

```json
{
  "mcpServers": {
    "tommkruix-archprint": {
      "command": "npx",
      "args": [
        "-y",
        "archprint",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 83, −10)

- [security regression] Known CVEs: fail → unverified
- [security] Known CVEs: CVE check failed: a known medium-severity CVE affects minimatch 10.2.5, a direct dependency. A fixed version is available.
- [functional regression] Schema quality: 173 → 219
- [functional regression] Dependency health: 0.87 → unverified
- [functional] Package version: 0.17.0 → 0.18.1
- [functional] Package version: 0.17.0 → 0.18.0

### 2026-11-04 (score 93, 0)

- [security regression] Stability: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.15.0 → 0.17.0
- [functional] Package version: 0.15.0 → 0.16.0

### 2026-11-01 (score 93, 0)

- [security] Stability: 0.97 → pass

### 2026-10-31 (score 93, +14)

- [security regression] CVE-2026-118764 affects this package: medium
- [security regression] Known CVEs: pass → fail
- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 79, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.14.0 → 0.15.0

### 2026-10-29 (score 94, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 93, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `archprint_scan` (~202 tokens)

Scan architecture rules

List the architecture rules this TypeScript repo already follows, with the evidence: each rule stated in plain words, whether it is AUTO (clears the confidence gate) or SUGGEST (short of it), its adoption ("enforce": archprint init or generate writes a rule for it, which archprint wire connects to the linter, and public-API rules need dependency-cruiser; "review": held for a human to review, not enforced by default; "report-only": the code follows it but archprint writes no rule for it), how many files conform vs. break it, the files that break it, and the confidence. Read-only. `path` defaults to "." and a monorepo root scans every app.

Input parameters:

- `deep` (boolean): resolve imports through barrels and aliases (slower, more accurate)
- `path` (string): app or monorepo-root directory on this machine (default "."), not a URL

### `archprint_recommend` (~97 tokens)

Recommend architecture rules

Recommend an architecture rule set for this repo from its evidence and detected stack: what to enforce now, what the code already follows that archprint reports but does not write a rule for yet (reportOnly), what to review before enforcing, and what comparable repos commonly adopt that this repo does not yet. Read-only.

Input parameters:

- `path` (string): app or monorepo-root directory on this machine (default "."), not a URL

### `archprint_explain` (~271 tokens)

Explain an architecture rule

Explain one rule from archprint_scan in depth, by its id, label or ESLint name (e.g. AP-002, env-access, no-lib-to-app, "lib !-> app" or archprint/no-lib-to-app): its statement, gate status, adoption (enforce, review, or report-only, as in archprint_scan), observed conformance and confidence floor, and every file that breaks it (scan lists only a few). For the forbidden-import rules (AP-001, AP-002) it also returns each confidence-gate condition with its value and threshold, how to fix a violation, and when not to adopt the rule. A rule the team stated in CLAUDE.md or AGENTS.md and adopted (its id starts with doc-) comes back with the sentence the team wrote, its source line, what it enforces in plain words, its evidence and its exceptions. Read-only.

Input parameters:

- `id` (string, required): rule id, label or ESLint name from archprint_scan, e.g. AP-002, no-lib-to-app or "lib !-> app", or a declared rule id such as doc-no-fetch-in-components
- `path` (string): app or monorepo-root directory on this machine (default "."), not a URL

### `archprint_gap_report` (~341 tokens)

Verify the rules in CLAUDE.md or AGENTS.md

Verify the rules a repo states in its context files (CLAUDE.md, AGENTS.md, .cursor/rules, ...) against its code. Read those files, then map each rule-like sentence to one template, quoting it exactly. archprint checks the quote is in the file and the mapping matches real files, measures how many files follow or break it, and returns a gap report: enforce now, enforce with a baseline (broken today, with the files), already an archprint rule, check the mapping, or guidance only. Show the report to the user: adopting a rule is their decision. Templates, with globs relative to `path` in ESLint syntax: "forbid-import" (files must not import `targets`, path globs matched on the file an import resolves to, or `packages`, specifier globs, each optionally limited to named `imports` such as {"name": "next/cache", "imports": ["unstable_cache"]}); "forbid-usage" (files must not use a global named in `usage`, such as "fetch", "window" or "process.env"); "forbid-file" (no new file may match `files`); "inferred" (the sentence is a rule archprint_scan lists; `rule` is its id); "none" (no template fits; give the `reason`, e.g. a style rule a standard linter covers). Read-only.

Input parameters:

- `mapping` (object, required): one entry per rule-like sentence
- `path` (string): repository root on this machine, where the context files are (default "."), not a URL

### `archprint_check` (~188 tokens)

Check a change against adopted rules

Check the current change, including uncommitted edits, against the rules this repo adopted with archprint init or generate, and report only the violations the change introduces (file, line, rule, and the evidence for the rule), plus those it fixed and any exceptions allowed with a reason in .archprint/config.json. Use it before finishing a change. Compares with `base` (a branch or commit, default origin/HEAD). Read-only: the files of the base commit are copied to a temporary folder outside the repo and deleted afterwards; it runs no git hooks and changes nothing in the repo. Returns status "skipped" with the reason when the repo has not adopted rules.

Input parameters:

- `base` (string): branch or commit to compare against (default origin/HEAD)
- `path` (string): repository directory where archprint was set up, on this machine (default ".")

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/tommkruix-archprint/archprint#diagnostics

## Score history

- 2026-11-05: 83
- 2026-11-04: 93
- 2026-11-03: 93
- 2026-11-02: 93
- 2026-11-01: 93
- 2026-10-31: 93
- 2026-10-30: 79
- 2026-10-29: 94
- 2026-10-28: 93
- 2026-10-27: 93
- 2026-10-26: 92
- 2026-10-25: 92
- 2026-10-24: 91
- 2026-10-23: 91
- 2026-10-22: 90
- 2026-10-21: 90
- 2026-10-20: 74
- 2026-10-19: 89
- 2026-10-18: 88
- 2026-10-17: 88
- 2026-10-16: 87
- 2026-10-15: 87
- 2026-10-14: 49
- 2026-10-13: 49
- 2026-10-12: 49
- 2026-10-11: 49
- 2026-10-05: 39
- 2026-10-04: 39
- 2026-10-03: 82
- 2026-10-02: 82

## Common questions

### What is the Archprint MCP server?

Archprint is an MCP server listed in the public MCP registry as io.github.Tommkruix/archprint. Mine the architecture rules your TypeScript repo already enforces, with the evidence attached. This page covers its npm package (archprint).

### Is the Archprint MCP server safe to use?

Archprint scores 83 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Archprint MCP server expose?

Archprint exposes 5 tools: archprint_scan, archprint_recommend, archprint_explain, archprint_gap_report, archprint_check. Their descriptions and schemas cost roughly 1,099 tokens of context every time the server is loaded.

### Is the Archprint MCP server still maintained?

Archprint is still listed as active in the MCP registry. We last reached this channel on 5 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 Archprint MCP server under?

Archprint declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Archprint MCP server?

VerifyMCP ran 14 checks on Archprint, covering Malware scan, Install scripts, Source repository, Provenance and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Archprint: Known CVEs and Dependency health. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/archprint
- Socket report: https://socket.dev/npm/package/archprint
- Repository: https://github.com/Tommkruix/archprint
- Changelog RSS feed: https://verifymcp.io/servers/tommkruix-archprint/archprint.xml
- Changelog JSON feed: https://verifymcp.io/servers/tommkruix-archprint/archprint/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/tommkruix-archprint/archprint.json
- HTML version of this page: https://verifymcp.io/servers/tommkruix-archprint/archprint