What is webtools-mcp-server CLAUDE.md?

A set of instructions for developing and using a Node.js MCP server that analyzes websites with browser automation. It covers HTML extraction, screenshots, debugging, performance checks, and Lighthouse audits, which are automated website-quality tests.

Installing, starting, testing, inspecting, and configuring the webtools MCP server for website analysis.

It gives an AI coding assistant the project’s setup commands, file conventions, and guidance for controlling which web-analysis tools load.

How misterboe/webtools-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to misterboe/webtools-mcp-server. 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/misterboe/webtools-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/misterboe/webtools-mcp-server

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/misterboe/webtools-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/misterboe/webtools-mcp-server/claude-md)

Your own site

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

Per session 2,102 This file is loaded in full into every session.

When invoked 2,102 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	$0.02102	$0.02102
Opus 5.5	$0.00841	$0.00841
Sonnet 5.5	$0.00420	$0.00420
Haiku 4.5	$0.00210	$0.00210

Measured 2mo ago against content hash f44c1590b2db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webtools-mcp-server 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 · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is a Model Context Protocol (MCP) server that provides comprehensive web analysis tools including HTML extraction, screenshot capture, debugging, performance analysis, and Lighthouse audits. The server is built with Node.js, uses Puppeteer for browser automation, and is designed to be used with Claude Desktop.

Commands

Development Commands

npm start - Start the MCP server
npm test - Run tests
npm run inspect - Start MCP Inspector for debugging and testing tools
npm install - Install dependencies
node src/index.js - Direct server execution

Installation & Usage

npm install -g @bschauer/webtools-mcp-server - Global installation
npx @bschauer/webtools-mcp-server - Direct execution via npx
node src/index.js --help - Show configuration help and token optimization options

Token Usage Optimization

Default: All tools loaded (~10.3k tokens)
ENABLED_TOOLS environment variable: Control which tools are loaded
--tools CLI argument: Override tool selection
Available presets: ALL, BASIC (~1k tokens), WEB, DEBUG, PERFORMANCE, FULL_ANALYSIS
Individual tools: Comma-separated list of specific tools

Architecture

Core Components

Entry Points:

src/index.js - Main entry point that starts the server
src/server.js - Server configuration and request handling

Tool System:

src/tools/ - Individual tool implementations
- html.js - HTML extraction and markdown conversion
- screenshot.js - Screenshot capture with device emulation
- debug.js - Debug console with layout thrashing detection
- lighthouse.js - Lighthouse audit integration
- performance/ - Performance analysis tools (trace, coverage, web vitals, network)

Configuration:

src/config/ - Configuration files
- tool-definitions.js - Tool schemas and parameter definitions
- capabilities.js - Server capabilities declaration
- devices.js - Device emulation profiles
- network_conditions.js - Network condition profiles

Read the full file on GitHub · 200 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 · 200 lines · 2,102 tokens per session scan A f44c1590b2db

Subscribe to this mod's changes

webtools-mcp-server CLAUDE.md is an instructions file published in the GitHub repository misterboe/webtools-mcp-server (0 stars, last pushed 1y ago), licensed MIT. It adds 2,102 tokens to every session, about $0.0084 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.

Analytics and metrics Browser automation

webtools-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
webtools-mcp-server CLAUDE.mdmisterboe/webtools-mcp-server	Instructions file	0	1y ago	MIT	A	2,102	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

webtools-mcp-server: Instructions file for Claude Code