agentmods.dev

browser-use

browser-use is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Saik0s/mcp-browser-use. Its token cost is not measured, scanned A, original, MIT.

An MCP server that lets an agent use browser automation through a Python-based setup. MCP is a way for an AI agent to call external tools.

In plain words
What is it for?
Use it for browser-based work when the required environment variable and Python setup are available.
Why use it?
It provides browser interaction for tasks that cannot be completed by reading or editing local files alone.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mcp-browser-use plugin — 1 skill, 1 hook, 1 MCP server shipped together

not rated 958 +1 6mo ago A scan tokens not measured original MIT
View the source file Saik0s/mcp-browser-use
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Saik0s/mcp-browser-use
Claude Code
/plugin install mcp-browser-use

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

Or install mcp-browser-use, the plugin that ships this one along with the rest of its 1 skill, 1 hook, 1 MCP server.

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-use

README.md
[![agentmods](https://agentmods.dev/badge/mcp/saik0s/mcp-browser-use/browser-use.svg)](https://agentmods.dev/mcp/saik0s/mcp-browser-use/browser-use)
Your own site
<a href="https://agentmods.dev/mcp/saik0s/mcp-browser-use/browser-use"><img src="https://agentmods.dev/badge/mcp/saik0s/mcp-browser-use/browser-use.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-use 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.

.mcp.json · 12 lines

What it actually says

{
  "browser-use": {
    "type": "stdio",
    "command": "python3",
    "args": [
      "${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server.py"
    ],
    "env": {
      "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/src"
    }
  }
}
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 · 12 lines scan A 588daaa72859

Subscribe to this mod's changes

browser-use is an MCP server published in the GitHub repository Saik0s/mcp-browser-use (958 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 2026-08-30.

Browser automation
Related

Other mcp servers, from other repositories

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.

epam/ai-dial-chat · not measured

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.

ihuzaifashoukat/x-use · not measured

camoufox-research

MCP server for browser research on the anti-detect Camoufox browser: search, page reading (incl. JS/SPA), batch fetch, clicks, typing, sessions, cache. Runs locally from the camoufox-research Python package.

aidvizhhub/camoufox-research · not measured

chrome-devtools

Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.

MadAppGang/dingo · not measured

mare-browser-mcp

Lean, LLM-first browser automation MCP server. Gives Claude, OpenCode, or any MCP client a real browser to navigate, interact with, and debug web apps. Runs locally from the mare-browser-mcp npm package.

emadklenka/mare_browser_mcp · not measured

crawlgraph-mcp

MCP server "crawlgraph-mcp" as configured in pucilpet/crawlgraph-mcp. Launched with https://github.com/pucilpet/crawlgraph-mcp/releases/download/v0.2.2/crawlgraph-m. Needs 1 environment variable to run.

pucilpet/crawlgraph-mcp · not measured