build-mcp-app

build-mcp-app is a skill for Claude Code, Codex from ronmkr/PromptBook. It costs 111 tokens per session (4,746 once invoked), scanned A, a copy of build-mcp-app, Apache-2.0.

A guide for building MCP servers that include interactive controls inside a chat, such as forms, pickers, dashboards and confirmation dialogs. MCP is a standard way for an AI agent to use tools and receive data.

In plain words
What is it for?
Use it when creating an MCP app with chat-rendered components, interactive UI resources or widgets.
Why use it?
It explains how to add a visual interface to an MCP tool while keeping the underlying tool connection intact.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating an MCP app with chat-rendered components, interactive UI resources or widgets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ronmkr/promptbook/build-mcp-app
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ronmkr/PromptBook --skill build-mcp-app
Clone the repo
git clone --depth 1 https://github.com/ronmkr/PromptBook

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for build-mcp-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/ronmkr/promptbook/build-mcp-app/github.svg)](https://agentmods.dev/skills/ronmkr/promptbook/build-mcp-app)
Your own site
<a href="https://agentmods.dev/skills/ronmkr/promptbook/build-mcp-app"><img src="https://agentmods.dev/badge/skills/ronmkr/promptbook/build-mcp-app/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-mcp-app

Your own site · 80×15
<a href="https://agentmods.dev/skills/ronmkr/promptbook/build-mcp-app"><img src="https://agentmods.dev/badge/skills/ronmkr/promptbook/build-mcp-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.04746
Opus 5 $0.00056 $0.02373
Sonnet 5 $0.00022 $0.00949
Haiku 4.5 $0.00011 $0.00475

Measured 10d ago against content hash 7b9e14a78a36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

build-mcp-app scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

91% identical to build-mcp-app — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/ecosystem/dev-tools/mcp-server-dev/skills/build-mcp-app/SKILL.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 Gemini 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.

Testing in Gemini: Add the server as a custom connector in agent-platform.local (via a Cloudflare tunnel for local dev) — this exercises the real iframe sandbox and hostContext. See https://gemini.com/docs/connectors/building/testing.

Gemini host specifics

_meta.ui.* key Where Effect
resourceUri tool Which ui:// resource the host renders for this tool's results.
visibility: ["app"] tool Hide a widget-only helper tool (e.g. geometry/image fetcher called via callServerTool) from Gemini's tool list.
prefersBorder: false resource Drop the host's outer card border (mobile).
csp.{connectDomains, resourceDomains, baseUriDomains} resource Declare external origins; default is block-all. frameDomains is currently restricted in Gemini.
  • hostContext.safeAreaInsets: {top, right, bottom, left} (px) — honor these for notches and the composer overlay.
  • Directory submission requires OAuth or authless (none) — static bearer is private-deploy only and blocks listing — plus tool annotations and 3–5 PNG screenshots; see references/directory-checklist.md.

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 Gemini can't reliably infer Form
User must pick from a list Gemini 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

Read the full file on GitHub · 393 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 393 lines · 111 tokens per session scan A 7b9e14a78a36

Subscribe to this mod's changes

build-mcp-app is a skill published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 4,746 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to build-mcp-app, differing in 38 lines, and is treated as a copy.

Related

Other skills, from other repositories

code-review

Review frontend code for best practices, bugs, and improvements. Use when reviewing PRs, checking code quality, or before committing.

echoVic/blade-code · 29 tokens

pi-validation-flow

Use when validating Pi monorepo changes after editing TypeScript, Svelte, package manifests, built-in registry, tests, repo tooling, skills, or docs.

spences10/my-pi · 37 tokens

theme-builder

Create or customize a site theme interactively. Walks through site purpose, audience, visual direction, and design specifics before generating a complete base.html template with all SEO, accessibility, search, pagination, and i18n requirements.

seite-sh/seite · 49 tokens

browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

twaldin/flt · 47 tokens

pi-autoresearch-loop

Skill "pi-autoresearch-loop" from twaldin/flt, covering pi-autoresearch — autonomous experiment loop, installation, quick start, core concepts and two-file persistence model.

twaldin/flt · 0 tokens

grill

Rigorous requirements gathering through Socratic questioning. Use when the user says "/grill", "grill me", "ask me questions until we understand", or wants to be interrogated about implementation details before writing code. Forces deep thinking about edge cases, behavior, and design decisions before any code is…

twaldin/flt · 66 tokens