build-mcp-app SKILL.md skillB

build-mcp-app from nota-america/forgecat-agent-profiles is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nota-america/forgecat-agent-profiles/build-mcp-app@v0.1.0

Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
nota-america/forgecat-agent-profiles
Path
profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_mcp-server-dev/for-forgecat/skills/build-mcp-app/SKILL.md
Versions recorded
1
Latest version
v0.1.0, committed Jun 10, 2026
Size
16,447 bytes
Repository stars
93
License
Apache-2.0

This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Build an MCP App (Interactive UI Widgets)

An MCP app is a standard MCP server that **also serves UI resources** — interactive components rendered inline in the chat surface. Build once, runs in Claude *and* ChatGPT and any other host that implements the apps surface.

The UI layer is **additive**. Under the hood it's still tools, resources, and the same wire protocol. If you haven't built a plain MCP server before, the `build-mcp-server` skill covers the base layer. This skill adds widgets on top.

---

## When a widget beats plain text

Don't add UI for its own sake — most tools are fine returning text or JSON. Add a widget when one of these is true:

| Signal | Widget type |
|---|---|
| Tool needs structured input Claude can't reliably infer | Form |
| User must pick from a list Claude can't rank (files, contacts, records) | Picker / table |
| Destructive or billable action needs explicit confirmation | Confirm dialog |
| Output is spatial or visual (charts, maps, diffs, previews) | Display widget |
| Long-running job the user wants to watch | Progress / live status |

If none apply, skip the widget. Text is faster to build and faster for the user.

---
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nota-america/forgecat-agent-profiles/build-mcp-app@sha256:e30e4a1090485320

The line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ndkpeqe3zwwutqkp.svg)](https://markdownregistry.com/a/art_ndkpeqe3zwwutqkp)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jun 10, 2026.

versioncommittedcommitsizeaudit
v0.1.0 latest2026-06-10 c645100 16,447 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16447 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

nota-america/forgecat-agent-profiles · 93 stars · license Apache-2.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ndkpeqe3zwwutqkp
GET https://markdownregistry.com/api/v1/resolve?ref=nota-america/forgecat-agent-profiles/build-mcp-app
GET https://markdownregistry.com/api/v1/blob/e30e4a1090485320a13301a1294c3a16bfa62195ab1f2c22550cb4caa995a4e0

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nota-america/forgecat-agent-profiles

api-and-interface-design SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/api-and-interface-design/SKILL.md · Guides stable API and interface design. Use when designing APIs,
git:20260916.3a6b22e · audit A · 93 stars
browser-testing-with-devtools SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/browser-testing-with-devtools/SKILL.md · Tests in real browsers via Chrome DevTools MCP. Use when building
git:20260916.3a6b22e · audit B · 93 stars
ci-cd-and-automation SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/ci-cd-and-automation/SKILL.md · Automates CI/CD pipeline setup. Use when setting up or modifying
git:20260610.c645100 · audit A · 93 stars
code-review-and-quality SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/code-review-and-quality/SKILL.md · Conducts multi-axis code review. Use before merging any change. Use
git:20260916.3a6b22e · audit A · 93 stars
code-simplification SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/code-simplification/SKILL.md · Simplifies code for clarity. Use when refactoring code for clarity
git:20260610.c645100 · audit A · 93 stars
constraint-driven-development SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/constraint-driven-development/SKILL.md · Establishes a project's quality bar as a written contract and stops
git:20260916.3a6b22e · audit A · 93 stars
context-engineering SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session,
git:20260916.3a6b22e · audit A · 93 stars
debugging-and-error-recovery SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/debugging-and-error-recovery/SKILL.md · Guides systematic root-cause debugging. Use when tests fail, builds
git:20260916.3a6b22e · audit A · 93 stars
deprecation-and-migration SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/deprecation-and-migration/SKILL.md · Manages deprecation and migration. Use when removing old systems,
git:20260916.3a6b22e · audit A · 93 stars
documentation-and-adrs SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/documentation-and-adrs/SKILL.md · Records decisions and documentation. Use when you need to document
git:20260916.3a6b22e · audit A · 93 stars
doubt-driven-development SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial
git:20260916.3a6b22e · audit A · 93 stars
frontend-ui-engineering SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/frontend-ui-engineering/SKILL.md · Builds production-quality, accessible, responsive user-facing UIs.
git:20260916.3a6b22e · audit A · 93 stars

Every file in nota-america/forgecat-agent-profiles

Other files named build-mcp-app

build-mcp-app SKILL.md skill
anthropics/claude-plugins-official · plugins/mcp-server-dev/skills/build-mcp-app/SKILL.md · This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP…
v0.1.0 · audit B · 46,363 stars
build-mcp-app SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_mcp-server-dev/for-codex/.agents/skills/build-mcp-app/SKILL.md · This skill should be used when the user wants to build an "MCP
v0.1.0 · audit B · 93 stars
build-mcp-app SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_mcp-server-dev/for-cursor/.cursor/skills/build-mcp-app/SKILL.md · This skill should be used when the user wants to build an "MCP
v0.1.0 · audit B · 93 stars
build-mcp-app SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_mcp-server-dev/for-claude/.claude/skills/build-mcp-app/SKILL.md · This skill should be used when the user wants to build an "MCP
v0.1.0 · audit B · 93 stars

Browse by kind, by grade B, or by owner.