convert-web-app

A guide for making an existing web app also work as an MCP App, so an AI assistant can display and interact with its interface. A hybrid app keeps its normal web use while adding this assistant integration.

In plain words
What is it for?
Use it to wrap a web app as an MCP App, convert a single-page app, or replace an iframe-based integration.
Why use it?
It helps reuse an existing website or single-page app instead of creating a separate MCP interface or relying on an embedded frame.

Skill for Claude CodeCodex

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/modelcontextprotocol/ext-apps/convert-web-app
Any agent
npx skills add modelcontextprotocol/ext-apps --skill convert-web-app
Clone the repo
git clone --depth 1 https://github.com/modelcontextprotocol/ext-apps

Made for: Claude Code, Codex.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.04644
Opus 5 $0.00057 $0.02322
Sonnet 5 $0.00023 $0.00929
Haiku 4.5 $0.00012 $0.00464

Measured yesterday against content hash f0d3a02fd4eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convert-web-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 yesterday.

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.

plugins/mcp-apps/skills/convert-web-app/SKILL.md · 526 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday First seen · 526 lines · 115 tokens per session scan A f0d3a02fd4eb

Subscribe to this mod's changes

convert-web-app is a skill published in the GitHub repository modelcontextprotocol/ext-apps (2,773 stars, last pushed 19d ago), with no licence file. It adds 115 tokens to every session and 4,644 once invoked, about $0.0006 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.