agentmods.dev

real-browser

real-browser is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from ofershap/real-browser-mcp. Its token cost is not measured, scanned A, original, MIT.

A local connection that lets an AI agent control a real Chrome browser through an MCP server and Chrome extension.

In plain words
What is it for?
It helps an agent open pages, inspect them, and interact with websites through your local Chrome session.
Why use it?
It lets the agent work with the browser you already use, including its current pages and logged-in sessions, instead of requiring a separate browser setup.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

not rated 49 4d ago A scan tokens not measured original MIT
View the source file ofershap/real-browser-mcp
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/ofershap/real-browser-mcp/real-browser
Clone the repo
git clone --depth 1 https://github.com/ofershap/real-browser-mcp

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 real-browser

README.md
[![agentmods](https://agentmods.dev/badge/mcp/ofershap/real-browser-mcp/real-browser.svg)](https://agentmods.dev/mcp/ofershap/real-browser-mcp/real-browser)
Your own site
<a href="https://agentmods.dev/mcp/ofershap/real-browser-mcp/real-browser"><img src="https://agentmods.dev/badge/mcp/ofershap/real-browser-mcp/real-browser.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

real-browser 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 5d 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.

server.json · 10 lines

What it actually says

{
  "real-browser": {
    "command": "npx",
    "args": [
      "-y",
      "real-browser-mcp"
    ],
    "env": {}
  }
}
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. 5d ago First seen · 10 lines scan A f130fab30c0e

Subscribe to this mod's changes

real-browser is an MCP server published in the GitHub repository ofershap/real-browser-mcp (49 stars, last pushed 4d 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 2026-08-30.

Browser automationaibrowser-automationchrome-extensionclaudecursormcp
Related

Other mcp servers, from other repositories

browseweave

Secure local browser bridge and MCP server for AI clients. Runs locally from the browseweave npm package.

xenitV1/browseweave · not measured

thinkrun

Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome. Runs locally from the @thinkrun/mcp npm package.

dundas/thinkrun · not measured

safari-mcp

Native Safari browser automation for AI agents — 80 tools, zero Chrome overhead. Runs locally from the safari-mcp npm package.

achiya-automation/safari-mcp · not measured

ai-browser

MCP server "ai-browser" as configured in AI-XiaoDao/ai-browser-mcp. Runs CEFbro/AI-Fbowser-Mcp/mcp_bridge.js with node. Needs 3 environment variables to run.

AI-XiaoDao/ai-browser-mcp · not measured

browser-mcp

Browser MCP — control your real Chrome from Claude Code. 34 tools, CAPTCHA solving, date pickers, autocomplete combobox, overlay dismissal, file upload, multi-session, human-in-the-loop. Runs locally from the @agent360/browser-mcp npm package.

Agent360dk/browser-mcp · not measured

browser-mcp

MCP server "browser-mcp" as configured in EndymionLee/PilotBrowseMCP. Runs BrowserPlugin\server\dist\index.js with node.

EndymionLee/PilotBrowseMCP · not measured