agentmods.dev

browser-tools

browser-tools is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from LEEI1337/phantom-neural-cortex. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that connects an AI agent to Playwright, a tool for controlling and testing web browsers.

In plain words
What is it for?
Connecting Playwright-based browser tools to the agent. The input does not list the specific browser actions available.
Why use it?
It lets the agent use browser automation through a local server rather than handling web-page interactions only by text.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

One of 16 entries in .mcp.json — they are configured in one file and arrive together.

not rated 5 6mo ago A scan tokens not measured original MIT
View the source file LEEI1337/phantom-neural-cortex
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 mcp/leei1337/phantom-neural-cortex/browser-tools
Clone the repo
git clone --depth 1 https://github.com/LEEI1337/phantom-neural-cortex

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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 browser-tools

README.md
[![agentmods](https://agentmods.dev/badge/mcp/leei1337/phantom-neural-cortex/browser-tools.svg)](https://agentmods.dev/mcp/leei1337/phantom-neural-cortex/browser-tools)
Your own site
<a href="https://agentmods.dev/mcp/leei1337/phantom-neural-cortex/browser-tools"><img src="https://agentmods.dev/badge/mcp/leei1337/phantom-neural-cortex/browser-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

browser-tools 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 3d 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.

.mcp.json · 11 lines

What it actually says

{
  "browser-tools": {
    "type": "stdio",
    "command": "npx",
    "args": [
      "-y",
      "@executeautomation/playwright-mcp-server"
    ],
    "env": {}
  }
}
Same file

What else .mcp.json configures

This page is one entry in a file that holds 16. Installing the file brings all of them; each is measured and scanned on its own page.

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. 3d ago First seen · 11 lines scan A c2239e4a12f7

Subscribe to this mod's changes

browser-tools is an MCP server published in the GitHub repository LEEI1337/phantom-neural-cortex (5 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 automationaiartificial-intelligenceautomationclaudegeminigithub-copilot
Related

Other mcp servers, from other repositories

openbrowser-ai

Agentic browser automation using LangGraph and raw CDP. Runs locally from the openbrowser-ai Python package. Needs 7 environment variables to run.

billy-enrizky/openbrowser-ai · not measured

prerenderbuddy

Local MCP tools for public crawler diagnostics and optional Prerender Buddy workspace evidence. Runs locally from the @prerenderbuddy/mcp npm package.

kopachlager/prerenderbuddy-plugins · not measured

wappmcp

TypeScript stdio MCP server and CLI for WhatsApp Web. Runs locally from the wappmcp npm package.

vaibhavpandeyvpz/wappmcp · not measured

democratize-quality

MCP Server for democratizing quality through browser automation and comprehensive API testing capabilities. Runs locally from the @democratize-quality/mcp-server npm package. Needs 1 environment variable to run.

uppadhyayraj/dq-awesomeqa · not measured

playwright

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

javiarmesto/ALDC-AL-Development-Collection · not measured

playwright

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

PavanMudigonda/zero-to-ai · not measured