playwright-parallel-mcp CLAUDE.md

playwright-parallel-mcp CLAUDE.md is an instructions file for coding agents from sumyapp/playwright-parallel-mcp. It costs 628 tokens per session, scanned A, original, MIT.

Repository instructions for `playwright-parallel-mcp`, an MCP server that lets multiple AI agents control separate browser sessions. Playwright is a browser-automation tool; each session has its own browser, context, and page.

In plain words
What is it for?
Installing, building, testing, and type-checking the server, as well as understanding its session manager and browser-isolation design.
Why use it?
Separate sessions prevent agents from interfering with one another through a shared browser, making parallel browser work easier to manage.

Instructions file

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/sumyapp/playwright-parallel-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sumyapp/playwright-parallel-mcp

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 playwright-parallel-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sumyapp/playwright-parallel-mcp/claude-md.svg)](https://agentmods.dev/instructions/sumyapp/playwright-parallel-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sumyapp/playwright-parallel-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sumyapp/playwright-parallel-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 628 This file is loaded in full into every session.
When invoked 628 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 $0.00628 $0.00628
Opus 5 $0.00314 $0.00314
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 4d ago against content hash c4ccd0499cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

playwright-parallel-mcp 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

An MCP (Model Context Protocol) server that enables multiple AI agents to simultaneously control independent browser instances. This solves the problem of existing browser automation MCP servers sharing browsers between sessions by providing isolated browser instances for each session.

Development Commands

pnpm install          # Install dependencies
pnpm build            # Build with tsup (outputs to dist/)
pnpm dev              # Build in watch mode
pnpm start            # Start the built server
pnpm test             # Run tests with vitest
pnpm typecheck        # TypeScript type checking

Architecture

src/
├── index.ts           # MCP server entry point, all tool definitions
└── session-manager.ts # Browser session management (singleton)

Core Design

  • SessionManager (Singleton): Manages sessions via Map<string, Session>. Each session has an independent Browser, BrowserContext, and Page
  • Session: Holds browser instance, console logs (max 1000 entries), and metadata
  • MCP Tools: Defined using server.tool() from @modelcontextprotocol/sdk with Zod schema validation

Adding New Tools

Add to src/index.ts:

server.tool(
  "tool_name",
  "Tool description",
  {
    sessionId: z.string(),
    param: z.string().optional()
  },
  async ({ sessionId, param }) => {
    const session = sessionManager.getSession(sessionId);
    if (!session) throw new Error(`Session not found: ${sessionId}`);
    // Implementation
    return {
      content: [{ type: "text", text: JSON.stringify(result) }]
    };
  }
);

Contribution Guidelines

Language

  • Code: All code, comments, and documentation must be in English
  • Commits: Write commit messages in English
  • Issues/PRs: Use English for all GitHub communication

Commit Message Format

Use concise, descriptive commit messages:

  • feat: add screenshot tool - New feature
  • fix: handle null session gracefully - Bug fix
  • docs: update README examples - Documentation
  • refactor: extract validation logic - Code improvement
  • test: add navigation edge cases - Test additions

Read the full file on GitHub · 89 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 · 89 lines · 628 tokens per session scan A c4ccd0499cd6

Subscribe to this mod's changes

playwright-parallel-mcp CLAUDE.md is an instructions file published in the GitHub repository sumyapp/playwright-parallel-mcp (17 stars, last pushed 8mo ago), licensed MIT. It adds 628 tokens to every session, about $0.0031 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.