What is mcp-ui-poc CLAUDE.md?

Project instructions for an application with an Express server, a React and Vite frontend, and an MCP-based user interface. It uses a two-package monorepo, meaning both packages live in one repository.

Use them when working on the server, client, glass-style interface, navigation, real-time appearance controls, or project validation.

They tell an AI coding assistant where to look first, how the interface is organised, and which workflow must be followed before making changes.

How iamadi11/mcp-ui-poc configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to iamadi11/mcp-ui-poc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/iamadi11/mcp-ui-poc/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/iamadi11/mcp-ui-poc

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/iamadi11/mcp-ui-poc/claude-md/github.svg)](https://agentmods.dev/instructions/iamadi11/mcp-ui-poc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/iamadi11/mcp-ui-poc/claude-md"><img src="https://agentmods.dev/badge/instructions/iamadi11/mcp-ui-poc/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/iamadi11/mcp-ui-poc/claude-md"><img src="https://agentmods.dev/badge/instructions/iamadi11/mcp-ui-poc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 531 This file is loaded in full into every session.

When invoked 531 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00531	$0.00531
Opus 5	$0.00266	$0.00266
Sonnet 5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 9d ago against content hash 6b9ae81c5cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-ui-poc CLAUDE.md 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 9d 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.

CLAUDE.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code — project context

Stack & layout

Stack: Node.js (ES modules), Express (server/), React 18 + Vite (client/), Tailwind CSS v4 + shadcn/ui in the shell (client/src/components/ui/), @mcp-ui usage in server MCP code paths.
Client UI: Glassmorphism-style layout (blur, mesh backdrop); light/dark follows system preference. Real-time glass tuning lives in client/src/glassAppearance.js and the Glass control in App.jsx (persisted in localStorage).
Monorepo: Two packages — root (server + scripts) and client/ (frontend). Install: npm install at root, npm run install-all for both.

Mandatory workflow

Follow docs/AI_WORKFLOW.md for the full sequence (research → plan → test definition → implement → tests → validate → document → instrument). Do not contradict that document; one-line exceptions with rationale only.

Use these first (see docs/AI_WORKFLOW.md for order):

Project docs: README.md, docs/AI_WORKFLOW.md, this file.
Scoped search: ripgrep/editor search within server/ or client/ before whole-repo sweeps.
MCP (when available in Claude Code / Cursor): cursor-ide-browser for web UI verification; user-ai-agent-committee if enabled — always read tool schemas before calling.

Do / don’t (project-specific)

Do keep API and static generation logic in server/; UI in client/src/.
Do use process.env for configuration; rely on .env locally (never commit secrets).
Do run npm run lint from client/ after changing JSX/JS once client/ has an ESLint config; until then use editor checks and npm run build (see README.md — Testing / quality).
Don’t commit .env, API keys, or machine-specific absolute paths in project config meant for everyone.
Don’t add secrets to prompts, logs, or generated MCP UI payloads.

Skills

Playbooks live under .claude/skills/ (see .claude/README.md). Use them for procedure; keep long reference material in docs/ and here.

Read the full file on GitHub · 32 lines

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.

9d ago First seen · 32 lines · 531 tokens per session scan A 6b9ae81c5cf8

Subscribe to this mod's changes

mcp-ui-poc CLAUDE.md is an instructions file published in the GitHub repository iamadi11/mcp-ui-poc (8 stars, last pushed 3mo ago), licensed MIT. It adds 531 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-ui-poc: Instructions file for Claude Code