What is cloud-mcp AGENTS.md?

Project instructions for building MCP Apps with a React user interface and a Python server. MCP Apps are small interactive tools that can run in AI assistants and developer tools that support MCP.

Use them when developing or reviewing widgets such as lists, QR-code generators, image galleries, dashboards, and interactive visualizations.

They give an agent a defined setup order, framework guidance, examples, and required checks for working in this repository.

How xkloveme/cloud-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to xkloveme/cloud-mcp. 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/xkloveme/cloud-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/xkloveme/cloud-mcp

Made for: Codex, OpenCode.

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/xkloveme/cloud-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/xkloveme/cloud-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xkloveme/cloud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xkloveme/cloud-mcp/agents-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/xkloveme/cloud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xkloveme/cloud-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,314 This file is loaded in full into every session.

When invoked 2,314 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	$0.02314	$0.02314
Opus 5.5	$0.00926	$0.00926
Sonnet 5.5	$0.00463	$0.00463
Haiku 4.5	$0.00231	$0.00231

Measured 2mo ago against content hash 38443db778a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloud-mcp AGENTS.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 2mo 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.

AGENTS.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

MCP App template: React widgets + Python MCP server. Build once, run on Claude, ChatGPT, VS Code, Goose, and other MCP hosts.

Quick Start (Follow These Steps)

1. Setup and Verify

./setup.sh   # Installs deps, builds, runs tests — must pass before continuing

2. Understand the Framework

Read in this order:

README.md — What MCP Apps are, why this template exists
docs/widget-development.md — Hook APIs and widget patterns

3. Review Examples (By Complexity)

Start with simpler examples and progress to advanced ones as needed:

Complexity	Widget	Description	Key Concepts
Beginner	`list`	Simple list display	Basic props, theme support
Beginner	`qr`	QR code generator	Single input, canvas rendering
Intermediate	`carousel`	Image slideshow	State management, navigation
Intermediate	`gallery`	Image grid	Grid layout, responsive design
Intermediate	`dashboard`	Stats cards	Multiple data types, layout
Advanced	`scenario-modeler`	Interactive charts	Chart.js, complex data
Advanced	`solar-system`	3D visualization	Three.js, animation loops
Advanced	`map`	Interactive maps	External APIs (Leaflet), geocoding

Recommended starting point: Examine the carousel widget:

Frontend: src/carousel/index.tsx (entry) + src/carousel/App.tsx (component)
Server: server/widgets/carousel.py — exports WIDGET, INPUT_MODEL, handle()

4. Create Your App

./create_new_app.sh --name my_app                    # Start fresh
./create_new_app.sh --name my_app --keep carousel    # Keep carousel as reference

Verify tests still pass after running the script.

5. Development Loop

For each widget you build:

# 1. Create src/my-widget/index.tsx + src/my-widget/App.tsx
# 2. Create server/widgets/my_widget.py (auto-discovered)
# 3. Build and test:
pnpm run build && pnpm run test
# 4. Visual verification:
pnpm run ui-test --tool show_my_widget
# 5. Check screenshot: /tmp/ui-test/screenshot.png
# 6. Iterate until tests pass and widget renders correctly

Read the full file on GitHub · 272 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.

2mo ago First seen · 272 lines · 2,314 tokens per session scan A 38443db778a8

Subscribe to this mod's changes

cloud-mcp AGENTS.md is an instructions file published in the GitHub repository xkloveme/cloud-mcp (0 stars, last pushed 9mo ago), licensed MIT. It adds 2,314 tokens to every session, about $0.0093 per session on Opus 5.5. 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.

Building agents

cloud-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cloud-mcp AGENTS.mdxkloveme/cloud-mcp	Instructions file	0	9mo ago	MIT	A	2,314	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

cloud-mcp: Instructions file for Codex