ecobrowser

ecobrowser is an MCP server for Claude Code, Codex, Cursor from HaidarESBER/ai-browser. Its token cost is not measured, scanned A, original, MIT.

A TypeScript browser framework and MCP server that lets an AI inspect and interact with websites through structured page information. It runs locally through the ecobrowser npm package.

In plain words
What is it for?
Use it to build TypeScript browser automation, connect browser abilities to an MCP-compatible AI client, inspect page changes, and interact with websites.
Why use it?
It gives an AI a way to see web pages and perform browser actions without relying only on screenshots or fixed coordinates. Its verified actions can recover when a page changes.

MCP server for Claude CodeCodexCursor

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/haidaresber/ai-browser/ecobrowser
Clone the repo
git clone --depth 1 https://github.com/HaidarESBER/ai-browser

Made for: Claude Code, Codex, Cursor.

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 ecobrowser

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

ecobrowser 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.

listed in the official MCP registry · 9 lines

What it actually says

{ "ecobrowser": { "command": "npx", "args": [ "-y", "ecobrowser" ] } }

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 · 9 lines scan A e6562f44773f

Subscribe to this mod's changes

ecobrowser is an MCP server published in the GitHub repository HaidarESBER/ai-browser (1 stars, last pushed 1mo 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.

Related

Other mcp servers, from other repositories

axstream

Fast, verified computer use for agents: a streaming JSONL action spec, a verified click ladder, and macros that make repeat tasks instant. Runs locally from the axstream Python package.

milind-soni/axstream · not measured

pixelcheck

Real eyes and hands on the web for AI agents. MCP-first. Local-first. Vendor-agnostic. Runs locally from the pixelcheck npm package. Needs 1 environment variable to run.

xcodethink/pixelcheck · not measured

deskcert

Certify whether an AI agent is safe to operate your internal web application before production rollout. Author a YAML task suite against your own app, run it with Playwright, and gate CI/CD on a forbidden-action safety score. Runs locally from the deskcert-cli Python package.

RudrenduPaul/DeskCert-CLI · not measured

desktop-mcp

Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, and screen-recording. Config-gated tool groups (observe/window/input/record) -- input disabled by default. Local-only, single-machine. Runs locally from the desktop-mcp Python package.

Zetakai/desktop-mcp · not measured

agentic-browser

AI Agent-First Browser: semantic web world model for LLM agents (library + MCP). Runs locally from the agentic-browser Python package.

applejuice093/Agentic-browser · not measured

hermes-computer-use

Pixel-level browser automation MCP server for WSL2 — drive a real Chrome with screenshot + xdotool, no CDP. Runs locally from the hermes-computer-use Python package.

Noah3521/hermes-computer-use · not measured