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.
git clone --depth 1 https://github.com/ofershap/real-browser-mcpWrote 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.
[](https://agentmods.dev/mcp/ofershap/real-browser-mcp/real-browser)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
What it actually says
{
"real-browser": {
"command": "npx",
"args": [
"-y",
"real-browser-mcp"
],
"env": {}
}
}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.
- 1mo ago First seen · 10 lines scan A f130fab30c0e
real-browser is an MCP server published in the GitHub repository ofershap/real-browser-mcp (57 stars, last pushed 2d 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.
Other mcp servers, from other repositories
thinkrun
Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome. Runs locally from the @thinkrun/mcp npm package.
browseweave
Secure local browser bridge and MCP server for AI clients. Runs locally from the browseweave npm package.
safari-mcp
Native Safari browser automation for AI agents — 80 tools, zero Chrome overhead. Runs locally from the safari-mcp npm package.
x-use
Browser-native AI agents for X (Twitter): multi-account, MCP-ready, no API keys required. Runs locally from the x-use-mcp Python package. Needs 2 environment variables to run.
browser-mcp
Browser MCP - the browser tool that can stop and ask you. A 2FA code, a CAPTCHA, a choice only you can make: it asks on your own screen, then carries on in the tab you were already signed into. 40 tools, any MCP client, MIT. Runs locally from the @agent360/browser-mcp npm package.
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.