What is php-mcp-apps?

A development guide for building MCP Apps in PHP. MCP Apps are tools that return both data and an interactive HTML view that compatible hosts can display inside a sandboxed panel.

Use it to build dashboards, forms, carousels, pickers, widgets, and other interactive views for PHP MCP servers.

It explains how to connect a PHP MCP tool to a live user interface while keeping the tool compatible with supported MCP hosts. This avoids having to design the communication between the view and the host from scratch.

php-mcp-apps — Skill by logiscape

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.

agentmods

npx agentmods add skills/logiscape/mcp-sdk-php/php-mcp-apps

Any agent

npx skills add logiscape/mcp-sdk-php --skill php-mcp-apps

Clone the repo

git clone --depth 1 https://github.com/logiscape/mcp-sdk-php

Made for: Claude Code, Codex.

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,040 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00175	$0.04040
Opus 5	$0.00088	$0.02020
Sonnet 5	$0.00035	$0.00808
Haiku 4.5	$0.00017	$0.00404

Measured 3d ago against content hash db1cb09737a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

php-mcp-apps 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 3d 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/skills/php-mcp-apps/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PHP MCP Apps Development Guide

Overview

MCP Apps (SEP-1865) let an MCP tool ship an interactive HTML view that the host — Claude, ChatGPT, VS Code Copilot, and others — renders in a sandboxed iframe next to the tool's result. It is the first official MCP extension (extension id io.modelcontextprotocol/ui, stable revision 2026-01-26, GA January 2026), jointly authored by Anthropic, OpenAI, and the MCP-UI community — which is why one correctly built app runs across ChatGPT, Claude, VS Code, Microsoft 365 Copilot, Goose, Postman, and more.

An MCP App is three things, and only three things:

An ordinary tool that returns both human-readable content and a machine-readable structuredContent payload.
A ui:// resource carrying a self-contained HTML document (MIME type text/html;profile=mcp-app) served via plain resources/read.
A _meta link (_meta.ui.resourceUri) on the tool pointing at that resource, plus the extensions capability declaration.

The extension adds no new server RPC. All interactivity — the view calling tools, posting messages to the chat, resizing — flows through the host over a postMessage JSON-RPC bridge (ui/* methods) that never touches your PHP code. Your server's job is small and this SDK compresses it into one call: McpServer::ui().

Why PHP is a great fit: the host fetches the view once and pushes data into it — so the server side is stateless request/response, exactly PHP's model. No Node build step (views are single-file vanilla HTML/JS), no long-running process, no SSE required. Apps built with this SDK deploy to cPanel/Apache shared hosting unchanged.

Prerequisite: a PHP 8.1+ project with the SDK installed (composer require logiscape/mcp-sdk-php). This skill covers everything UI; for general server fundamentals (tool design, transports, sessions, OAuth) consult the SDK's own documentation — the README at https://raw.githubusercontent.com/logiscape/mcp-sdk-php/main/README.md and the guides it links under docs/ (fetch with WebFetch as needed).

Read the full file on GitHub · 306 lines

Files

What ships with it

5 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.

3d ago First seen · 306 lines · 175 tokens per session scan A db1cb09737a7

Subscribe to this mod's changes

php-mcp-apps is a skill published in the GitHub repository logiscape/mcp-sdk-php (369 stars, last pushed 13d ago), licensed MIT. It adds 175 tokens to every session and 4,040 once invoked, about $0.0009 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 2026-08-30.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens