What is browser-automacao-referencia?

A Portuguese-language reference guide to the concepts behind a browser MCP server, including how it communicates with Chrome and the different browser-control modes. MCP is a standard for connecting an assistant to tools.

Learning how the browser server uses Playwright, Chrome DevTools Protocol, and a Chrome extension, with code locations and practical consequences.

It explains unfamiliar browser-automation concepts in the context of the codebase and points to where they appear in the repository.

How flpccabral/mcp-browser configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to flpccabral/mcp-browser. 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/flpccabral/mcp-browser/main/.claude/skills/browser-automacao-referencia/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/flpccabral/mcp-browser

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/skills/flpccabral/mcp-browser/browser-automacao-referencia/github.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-automacao-referencia)

Your own site

<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-automacao-referencia"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-automacao-referencia/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/skills/flpccabral/mcp-browser/browser-automacao-referencia"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-automacao-referencia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 332 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,698 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00332	$0.06698
Opus 5.5	$0.00133	$0.02679
Sonnet 5.5	$0.00066	$0.01340
Haiku 4.5	$0.00033	$0.00670

Measured 2mo ago against content hash b227dd3a7885, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-automacao-referencia 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/skills/browser-automacao-referencia/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referência de Automação de Browser — a teoria por trás deste código

Este é o pacote de teoria do domínio que um engenheiro pleno normalmente não tem, explicado como se aplica AQUI — não como livro-texto. Cada conceito traz: definição curta, onde aparece neste repositório (arquivo:linha) e a consequência prática. Fatos voláteis estão datados de 2026-07-12; re-verifique com a última seção.

Esta skill é a teoria. As decisões de design que se apoiam nela estão em browser-mcp-contrato-de-arquitetura. A aplicação prática (triagem de falhas) está em browser-mcp-playbook-de-depuracao e browser-mcp-arqueologia-de-falhas.

Definições usadas uma vez, valendo para o documento inteiro:

Substrato — a camada técnica que efetivamente controla o Chrome. Há três: Playwright gerenciado, CDP sobre Chrome existente, e extensão MV3 via WebSocket.
Modo — o campo BrowserManager._mode ("playwright" | "cdp" | "extension"), declarado em src/browser_mcp/browser_manager.py:113.
Bridge — o par extensão Chrome + servidor WebSocket que liga o mundo Python ao Chrome real do usuário (extension/ + src/browser_mcp/websocket_server.py).

1. MCP (Model Context Protocol)

O que é. MCP é um protocolo JSON-RPC em que um servidor expõe tools a um client (o modelo/host). O transporte aqui é stdio: o processo servidor lê requisições e escreve respostas pelos file descriptors padrão. Um client MCP chama uma tool enviando name (string) + arguments (objeto JSON); o servidor devolve conteúdo (aqui, TextContent).

Onde aparece.

Transporte stdio e loop principal: src/browser_mcp/server.py:77 (stdio_server()) e server.py:77 (server.run(...)).
Handshake de listagem: server.py:18-21 — @server.list_tools() retorna app.get_tools().
Despacho de execução: server.py:24-30 — @server.call_tool() recebe name: str, arguments: dict e roteia para app.call_tool(name, arguments).
Registro real das tools: decorator @app.tool(...) em src/browser_mcp/tools.py (definição do ToolRegistry em tools.py:19; get_tools() monta types.Tool com inputSchema em tools.py:49; call_tool() roteia por nome em tools.py:62).

Read the full file on GitHub · 422 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 · 422 lines · 332 tokens per session scan A b227dd3a7885

Subscribe to this mod's changes

browser-automacao-referencia is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 3mo ago), licensed MIT. It adds 332 tokens to every session and 6,698 once invoked, about $0.0013 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.

Browser automation

browser-automacao-referencia next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browser-automacao-referenciaflpccabral/mcp-browser	Skill	0	3mo ago	MIT	A	332	Claude Code
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code

mcp-browser: Skill for Claude Code