MCP.Market

Agentic Browser MCP server

by davarion-tech·io.github.davarion-tech/agentic-browser·v1.3.0·3 stars
No reviews yet

Give any AI agent your real Chrome: text perception, visible cursor, ~4x fewer tokens.

B75/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
Growing

3 stars337 downloads/wk

Reviews

Write one

Nobody has reviewed Agentic Browser yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agentic Browser tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it

2 medium
  • Code scan15 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (2)

  • mediumnpm install lifecycle script presentinstall.script
  • mediumnpm install lifecycle script presentinstall.script
    package.json: … test/watcher.claude-code.test.js", "postinstall": "node scripts/postinstall.js" }, "k…
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agentic Browser compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% of 807 Scraping and browsing servers
GitHub stars
3
more than 68% of 553 Scraping and browsing servers
Downloads a week
337
more than 80% of 295 Scraping and browsing servers with a package

Install Agentic Browser in Claude Code, Cursor or VS Code

Runs npx -y agentic-browser-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agentic-browser -- npx -y agentic-browser-mcp
Add to Cursor

What the publisher says

From the Agentic Browser repository's README, as published. We do not edit it. Read it on GitHub

agentic-browser

Give any AI agent a real browser and watch everything it does.

Built and maintained by Davarion.

No API key. No extra bill. agentic-browser is a tool, not a model: it runs on your computer and uses whatever brain your agent already has. That can be your Claude Pro/Max plan in Claude Code, your ChatGPT plan in Codex, Cursor, or a local model. Nothing to sign up for and no per-token charges from us.

Humans browse the web with browsers. Agents usually need APIs. agentic-browser lets any agent use your installed Google Chrome the way a person does. It perceives pages as compact text with pixel coordinates instead of screenshots, and a visible cursor shows every move and click.

Español · Use cases · Chat watcher · Architecture · Security · Disclaimer

▶ Watch the 15-second demo · ▶ Watch the full video (1 min)

Real runs recorded by the agent itself: compare prices · research the web · fill a form and stop before submitting.

Why

Quick start

One line (Claude Code):

claude mcp add agentic-browser -- npx -y agentic-browser-mcp

Any other MCP client: use "command": "npx", "args": ["-y", "agentic-browser-mcp"]. Requirements: Node ≥ 18 and Chrome (or Edge).

From source

Requirements: Node ≥ 18 and Google Chrome.

git clone https://github.com/davarion-tech/agentic-browser.git
cd agentic-browser && npm install
npm run doctor
npm test

Use it from an MCP client

Claude Code:

claude mcp add agentic-browser -- node /absolute/path/to/agentic-browser/src/mcp.js

Claude Desktop, Cursor, Codex, Hermes, OpenClaw or any MCP client: see examples/mcp-config.json.

Claude Code slash command (optional): copy skills/agentic-browser into ~/.claude/skills/. Then /agentic-browser always uses this browser instead of any other built-in browser tool.

Then ask your agent something like:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agentic Browser: common questions

Is Agentic Browser MCP server safe?
Mostly: it is graded B (75/100). Read the Agentic Browser safety report
How do I install Agentic Browser?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agentic Browser need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agentic Browser maintained?
The last commit was 2 days ago (2026-10-23). The latest release is v1.3.0.
What can I use instead of Agentic Browser?
Servers from other publishers that do the same job: Public Browser MCP server, Tap MCP server and TabRunner MCP server. Compare all Agentic Browser alternatives.
How does Agentic Browser compare with other Scraping and browsing MCP servers?
safety score 75/100 (higher than 45% of 807 Scraping and browsing servers); github stars 3 (more than 68% of 553 Scraping and browsing servers); downloads a week 337 (more than 80% of 295 Scraping and browsing servers with a package). Full comparison.

Alternatives to Agentic Browser

Same job from other publishers: the closest match first, then the best rated.

All Agentic Browser alternatives →
  • Public Browser
    Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
    A
  • Tap
    Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
    B
  • TabRunner
    Give browser tasks to TabRunner, an agent in your own Chrome that uses your logins.
    A
  • Safari
    Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead.
    C
  • Agent360 Browser MCP
    Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.
    A