What is webappmcp CLAUDE.md?

Development instructions and architecture notes for a web-app MCP server. MCP, or Model Context Protocol, lets AI assistants use tools provided by other programs.

Use them when developing, testing, or extending a server that inspects web pages, simulates user actions, and reads application state in React, Vue, Angular, or plain JavaScript apps.

They give contributors a shared explanation of how the server, Express middleware, WebSocket connections, and browser-side code fit together.

How cgaspard/webappmcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cgaspard/webappmcp. 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/cgaspard/webappmcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cgaspard/webappmcp

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/cgaspard/webappmcp/claude-md/github.svg)](https://agentmods.dev/instructions/cgaspard/webappmcp/claude-md)

Your own site

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

Per session 2,786 This file is loaded in full into every session.

When invoked 2,786 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	$0.02786	$0.02786
Opus 5.5	$0.01114	$0.01114
Sonnet 5.5	$0.00557	$0.00557
Haiku 4.5	$0.00279	$0.00279

Measured 2mo ago against content hash 0a7f59b09d05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webappmcp 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 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.

CLAUDE.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebApp MCP Server - Development Guide

Project Overview

This project creates an MCP (Model Context Protocol) server that enables AI assistants to interact with web applications through a comprehensive set of tools. The server acts as a bridge between AI models and web applications, providing DOM inspection, user interaction simulation, and application state management capabilities.

Core Architecture

1. MCP Server Component

Node.js-based MCP server that exposes tools for web application interaction
Communicates with both backend Express middleware and frontend client
Manages WebSocket connections for real-time DOM access

2. Express Middleware

Installable as npm package dependency
Integrates with existing Express applications
Handles MCP server requests and routes them to appropriate handlers
Manages WebSocket server for client connections

3. Frontend Client Library

Framework-agnostic JavaScript library
Supports React, Vue, Angular, and vanilla JS applications
Establishes WebSocket connection to backend
Executes DOM operations requested by MCP server
Captures and transmits application state

Key Features

DOM Inspection Tools

Query elements using CSS selectors
Get element properties, attributes, and computed styles
Traverse DOM tree (parents, children, siblings)
Get text content and HTML structure
Monitor DOM mutations

User Interaction Simulation

Click elements
Type text into input fields
Submit forms
Hover over elements
Scroll page or elements
Drag and drop operations

Application State Access

Read JavaScript object properties
Access component state (framework-specific)
Monitor console logs
Intercept network requests
Access local storage and session storage

Visual Capture

Take full page screenshots
Capture specific element screenshots
Record user interaction sequences
Get element bounding boxes and positions

Implementation Details

Package Structure

webappmcp/
├── packages/
│   ├── server/          # MCP server implementation
│   ├── middleware/      # Express middleware
│   └── client/          # Frontend client library
├── examples/            # Example applications
└── docs/               # Documentation

Read the full file on GitHub · 359 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 · 359 lines · 2,786 tokens per session scan A 0a7f59b09d05

Subscribe to this mod's changes

webappmcp CLAUDE.md is an instructions file published in the GitHub repository cgaspard/webappmcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 2,786 tokens to every session, about $0.0111 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.

Backend and APIs

webappmcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
webappmcp CLAUDE.mdcgaspard/webappmcp	Instructions file	0	8mo ago	MIT	A	2,786	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

webappmcp: Instructions file for Claude Code