MCP.Market

HIG Doctor MCP server

by raintree-technology·io.github.raintree-technology/hig-doctor·v0.2.3·145 stars
No reviews yet

Apple Human Interface Guidelines search, lookup, and project audits for AI coding agents.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Established

145 stars74 downloads/wk

Reviews

Write one

Nobody has reviewed HIG Doctor yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

HIG Doctor tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • hig_auditwrite action

    Run a HIG compliance audit on a project directory. Scans source files across SwiftUI, UIKit, React, Vue, Svelte, Angular, Compose, Android XML, React Native, Flutter, CSS, and HTML. Returns severity counts (critical/serious/moderate), per-category breakdown, and a markdown report with code excerpts and HIG reference material. Honors hig-doctor.config.json, .hig-baseline.json, and inline hig-disabl

  • hig_audit_file

    Audit a single source file for HIG compliance \u2014 the fast inner loop after writing or editing a file. Returns every finding with its rule ID, severity, line, fix guidance, and HIG citation. Use hig_explain_finding for deeper guidance on a specific rule.

  • hig_explain_finding

    Explain an audit finding: full rule metadata (severity, engine, fix guidance) plus an excerpt of the Apple HIG reference the rule cites. Pass the ruleId from hig_audit / hig_audit_file results (e.g. 'swift/hardcoded-color').

  • hig_list_skills

    List all available Apple HIG skills with descriptions and reference topics. Use this first to discover what HIG guidance is available before calling hig_lookup.

  • hig_lookup

    Fetch Apple HIG reference markdown. Provide a skill name (e.g. 'hig-foundations') to get the skill overview, or a skill+topic (e.g. skill='hig-foundations', topic='color') to get detailed reference for that topic. Content is from Apple's HIG, snapshot dated

  • hig_search

    Full-text search (BM25) across all Apple HIG reference topics. Ask in natural language \u2014 e.g. 'minimum touch target size', 'when to use a sheet vs a popover' \u2014 and get ranked topics with snippets. Follow up with hig_lookup using the returned skill/topic.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

1 medium
  • Code scan2 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/index.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How HIG Doctor compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 70% of 3,470 Web search servers
Tools
6
the typical Web search server has 5
Tools that change things
17%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
145
more than 95% of 1,786 Web search servers
Downloads a week
74
more than 50% of 827 Web search servers with a package

What its tools let an agent do: 5 read · 1 change

Install HIG Doctor in Claude Code, Cursor or VS Code

Runs npx -y hig-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add hig-doctor -- npx -y hig-mcp
Add to Cursor

What the publisher says

From the HIG Doctor repository's README, as published. We do not edit it. Read it on GitHub

HIG Doctor

<!-- project-record: hig-doctor -->

Active open-source project · MIT tooling with attributed Apple reference content

HIG Doctor helps developers and coding agents find interface issues before release. It checks Apple-platform source against Apple’s Human Interface Guidelines and checks web and cross-platform source against aligned accessibility and interface-quality rules.

Run an audit

npx hig-doctor .

The CLI detects the project frameworks, reports concerns by severity, and points to a specific fix and source reference. This result is generated from the committed test/fixtures/readme-audit project and checked in the test suite:

2 moderate concerns · swiftui · 1 file
View.swift:5 · swift/navigation-view-deprecated
View.swift:7 · swift/hardcoded-color

The audit catalog currently contains 431 rules across 14 frameworks. Counts are generated from the rule catalog and checked in CI; they are coverage inventory, not a claim of complete HIG conformance.

Why use HIG Doctor

fix guidance, and the reference that supports the concern.

  • Catch reviewable source issues. Findings include severity, location, rule ID,

SARIF, and --fail-on support gradual adoption.

  • Gate only new debt. Configuration, inline suppressions, content-based baselines,

explain individual findings without presenting generated advice as canonical HIG.

  • Give agents bounded guidance. MCP tools search the frozen reference corpus and

share the same catalog and analysis tiers.

  • Use one engine across workflows. The CLI, MCP server, and embeddable core package

Choose a surface

The MCP server works over stdio or streamable HTTP. Its six tools list skills, look up topics, search the corpus, audit projects or files, and explain findings. See the MCP package README for client configuration.

Install the public Codex marketplace first with codex plugin marketplace add raintree-technology/plugins.

How analysis works

framework detection → regex scan → structural refinement → categorized findings → report or SARIF
  • The zero-dependency regex tier is comment- and string-aware.
  • Swift structural analysis follows chained modifiers to remove handled findings.
  • The TypeScript compiler refines selected JSX accessibility checks when available.
  • Every finding records the engine that produced it.

Precision and recall are measured on an annotated fixture corpus in docs/benchmark.md. CI enforces the published floors.

Framework coverage

Apple-platform rows are checked against the HIG directly. Web and cross-platform rows use universal accessibility and interface-quality principles that align with the HIG.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

HIG Doctor: common questions

Is HIG Doctor MCP server safe?
Mostly: it is graded B (83/100). Read the HIG Doctor safety report
How do I install HIG Doctor?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does HIG Doctor need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is HIG Doctor maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v0.2.3.
What can I use instead of HIG Doctor?
Servers from other publishers that do the same job: Repomix MCP server, Bitbybit CAD MCP server and ContextStream MCP Server.
How does HIG Doctor compare with other Web search MCP servers?
safety score 83/100 (higher than 70% of 3,470 Web search servers); tools 6 (the typical Web search server has 5); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to HIG Doctor

Same job from other publishers: the closest match first, then the best rated.

  • Repomix
    Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
    A
  • Bitbybit CAD MCP
    Bitbybit 3D parametric CAD API, version-exact, for coding agents: search, describe, examples, guide
    A
  • ContextStream MCP Server
    The context platform for AI agents: code search, team decisions, and grounded project context.
    A
  • Misakanet
    Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
    A
  • Ref Tools
    Token-efficient search for coding agents over public and private documentation.
    A