agentmods.dev

FerrumMCP CLAUDE.md

FerrumMCP CLAUDE.md is an instructions file for coding agents from Eth3rnit3/FerrumMCP. It costs 3,167 tokens per session, scanned A, original, MIT.

Development instructions for FerrumMCP, a browser automation server that lets AI assistants control browsers through the Model Context Protocol. It uses Ferrum, a Ruby driver for headless Chrome, and organises more than 27 tools into browser-operation categories.

In plain words
What is it for?
Use them when working on browser sessions, navigation, page interaction, waiting, data extraction, or advanced browser automation.
Why use it?
They explain the server's session-based design and how browser tools are organised, helping contributors understand where automation behaviour belongs.

Instructions file

not rated 30 8mo ago A scan 3,167 tokens original MIT
View the source file Eth3rnit3/FerrumMCP
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 instructions/eth3rnit3/ferrummcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Eth3rnit3/FerrumMCP

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.

agentmods badge for FerrumMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eth3rnit3/ferrummcp/claude-md.svg)](https://agentmods.dev/instructions/eth3rnit3/ferrummcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eth3rnit3/ferrummcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eth3rnit3/ferrummcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,167 This file is loaded in full into every session.
When invoked 3,167 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03167 $0.03167
Opus 5 $0.01584 $0.01584
Sonnet 5 $0.00633 $0.00633
Haiku 4.5 $0.00317 $0.00317

Measured 4d ago against content hash 54559ed65673, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FerrumMCP 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 4d 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 · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 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.

Project Overview

FerrumMCP is a browser automation server implementing the Model Context Protocol (MCP). It provides AI assistants with browser automation capabilities through a standardized interface, using Ferrum (Ruby's headless Chrome driver) and optional BotBrowser integration for anti-detection.

Architecture

Core Components

Server Layer (lib/ferrum_mcp/bin/ferrum-mcp)

  • FerrumMCP::Server: Main MCP server implementation
  • Manages 27+ browser automation tools organized into 6 categories (Session Management, Navigation, Interaction, Extraction, Waiting, Advanced)
  • Tools are defined in TOOL_CLASSES constant and registered with the MCP server at initialization
  • Session-based architecture: All browser operations require an explicit session

Session Management (lib/ferrum_mcp/session_manager.rb, lib/ferrum_mcp/session.rb)

  • SessionManager: Thread-safe session pool with automatic cleanup
  • Session: Encapsulates a browser instance with custom configuration
  • Supports multiple concurrent browser sessions with different configurations
  • Each session can use different browser types (Chrome, BotBrowser), options, and profiles
  • Session lifecycle: create → use → auto-cleanup (after 30min idle) or manual close
  • Important: All browser tools require a valid session_id parameter

Browser Management (lib/ferrum_mcp/browser_manager.rb)

  • BrowserManager: Handles Ferrum browser lifecycle
  • Supports both standard Chrome/Chromium and BotBrowser (anti-detection mode)
  • Browser options configured via browser_options method with anti-automation flags
  • Each session has its own BrowserManager with custom configuration

Transport Layer (lib/ferrum_mcp/transport/)

  • Two transport implementations:
    • HTTPServer: Uses MCP's StreamableHTTPTransport with Puma/Rack
    • StdioServer: Uses MCP's StdioTransport for standard I/O communication
  • Transport is selected at startup via --transport flag (http or stdio)

Read the full file on GitHub · 342 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.

  1. 4d ago First seen · 342 lines · 3,167 tokens per session scan A 54559ed65673

Subscribe to this mod's changes

FerrumMCP CLAUDE.md is an instructions file published in the GitHub repository Eth3rnit3/FerrumMCP (30 stars, last pushed 8mo ago), licensed MIT. It adds 3,167 tokens to every session, about $0.0158 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.

Browser automation
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

fix-quera AGENTS.md

Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.

AlirezaKeshavarz83/fix-quera · 1,338 tokens

fast-browser CLAUDE.md

Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.

m4ttstack/fast-browser · 1,446 tokens

sendblue-browser-use AGENTS.md

Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).

sendblue-api/sendblue-browser-use · 1,064 tokens

sniff AGENTS.md

AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.

Aboudjem/sniff · 1,901 tokens

browser_oxide AGENTS.md

AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.

yfedoseev/browser_oxide · 1,202 tokens