Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Applied Form engine

NPM · @APPLIEDFORM/ENGINE

Lint rendered pages against a design system in a real browser, across six widths, with the fix.

Available components

+4 this week 80 Trust /100

Last scanned (23 hours ago)

Scores higher than 65% of npm servers

Category Testing and QA

Deprecated

This server is marked deprecated in the MCP registry. The registry records this reason: Renamed: use io.github.Applied-Form/standards.

Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 2 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency68
  • Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
  • Cryptographically verified build provenance (signed, bound to Applied-Form/engine). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Maintenance check failed: the publisher has marked this version as deprecated on the registry, telling users to stop installing it. See how to fix → Fail
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability70
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 816 tokens (~90/item across 9 items; 9 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
  • Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 68% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Changelog

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 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +1
    • Security disclosure: unverified → pass ▲ functional
  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 29 Oct 26 0
    • Security disclosure: pass → unverified ▼ functional
  • 27 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Oct 26 −1
    • Maintenance: pass → fail ▼ functional
  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

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/@appliedform/engine@3.3.1

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo Applied-Form/engine
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Applied-Form/engine/.github/workflows/release.yml@refs/tags/v3.3.1
Rekor log index 3419004438
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:9036881ecbeb72d9ced9ba3111b9dafbe7ec0fdd1d7f767eb9d34a78bd2a5ffe7c1e6f51f88419b933a111679de8b67a147cc0c5f5c3f3c7fef3f83d9

Background: How many MCP packages publish verified provenance →

Dependencies 2 packages
Packages resolved 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~816 tokens

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 →

Tool Tokens
af_brand ~56

Derive a complete palette from a hue and a paper colour, measured against every floor, or refuse it with the reasons. Use this instead of inventing a palette.

NameTypeReqDescription
huenumberyes–
paperstringyes–

No output schema declared.

No examples provided.

af_contrast ~74

Measure a foreground against a background: the WCAG 2 ratio, the floor required at that size and weight, whether it passes, and the APCA reading as an advisory.

NameTypeReqDescription
backgroundstringyes–
foregroundstringyes–
sizePxnumber––
weightnumber––

No output schema declared.

No examples provided.

af_drift ~160

Measure what a design system actually is on pages that were not built to this one, and how far they have drifted from it: the palette, spacing step and type scale in use, plus how many values are indistinguishable duplicates. Use this to learn somebody else's system before working in it, rather than guessing from a screenshot.

NameTypeReqDescription
declaredarray–Hex colours the organisation publishes, to report where the guideline and the site disagree.
htmlarray–Complete HTML documents to measure.
urlsarray–file:// or https:// pages to measure instead. More pages give a truer system; one page gives one page's habits.
viewportsarray–Widths to measure. Defaults to 1280.

No output schema declared.

No examples provided.

af_fix ~144

Apply the fixes the engine can make on its own to a draft, measured in a real browser, and return the fixed HTML with a report: rules fixed, patches applied and refused, and what still fails, by element. No model is called, and a fix that makes any rule worse is not applied. Pass html; what remains needs a change to the markup.

NameTypeReqDescription
htmlstringyesA complete HTML document to fix.
registerstring–Which register the page is in, if the document does not declare it.
viewportsarray–Widths to measure and fix at. Defaults to the system's four plus two sampled from between them.

No output schema declared.

No examples provided.

af_lint ~133

Measure a page against the design system in a real browser and return every violation with the fix. Pass html for a draft, or url for something already served. This is the loop: draft, lint, apply the fixes, lint again.

NameTypeReqDescription
htmlstring–A complete HTML document to measure.
registerstring–Which register the page is in, if the document does not declare it.
urlstring–A file:// or https:// page to measure instead.
viewportsarray–Widths to measure. Defaults to the system's four plus two sampled from between them.

No output schema declared.

No examples provided.

af_move ~62

The recipe for a named compositional move: its cells, layers, voices and ground. One move is active per artefact; ask for the one you need rather than reading all of them.

NameTypeReqDescription
namestring–Omit to list the moves that exist.

No output schema declared.

No examples provided.

af_rules ~66

Every rule the gate enforces: what it requires, why, how to fix it, and which WCAG criteria it touches. Filter by group to keep the answer small.

NameTypeReqDescription
groupstring––
wcagboolean–Only rules that touch a WCAG criterion.

No output schema declared.

No examples provided.

af_system ~58

Read a design system authored elsewhere (a Standards pack tokens.json) into this one, reporting what it stated, what had to be derived, and what could not be carried across.

NameTypeReqDescription
packobjectyesThe pack's token contract, parsed.

No output schema declared.

No examples provided.

af_tokens ~63

The values the system permits: colours, spacing scale, type scale, voices, floors, ratios, and what it declares absent. Ask for this instead of guessing a value.

NameTypeReqDescription
groupstring–colour, spacing, type, floors, absent — omit for all.

No output schema declared.

No examples provided.

Install

How do I install the Applied Form engine MCP server?

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

npm · @appliedform/engine

# add to Claude Code
claude mcp add applied-form-engine -- npx -y @appliedform/engine
Common questions

What is the Applied Form engine MCP server?

Applied Form engine is an MCP server listed in the public MCP registry as io.github.Applied-Form/engine. Lint rendered pages against a design system in a real browser, across six widths, with the fix. This page covers its npm package (@appliedform/engine).

Is the Applied Form engine MCP server safe to use?

Applied Form engine scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. 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 Applied Form engine MCP server expose?

Applied Form engine exposes 9 tools: af_lint, af_fix, af_rules, af_tokens, af_contrast, and 4 more. Their descriptions and schemas cost roughly 816 tokens of context every time the server is loaded.

Is the Applied Form engine MCP server still maintained?

Applied Form engine is marked deprecated 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 Applied Form engine MCP server under?

Applied Form engine declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.