Crawlio Browser MCP Server

Use Crawlio Browser when your AI needs to interact with a real browser - SPAs, authenticated pages, dynamic content, JS-rendered frameworks. Unlike headless browser tools, Crawlio Browser connects to your actual Chrome via a lightweight extension, giving the AI access to your logged-in sessions, cookies, and full browser state. It runs locally over stdio via the published package.

People connecting browser automation tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-10 · ★ 6 · #49 OF 196 MAINTAINED BROWSER AUTOMATION · VERIFIED 2026-08-25

Apache-2.0 · TypeScript servers · how we verify → /methodology

01 · Install Crawlio Browser

Claude Code

claude mcp add crawlio-app-crawlio-browser -- npx -y crawlio-browser

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "crawlio-app-crawlio-browser": {
      "command": "npx",
      "args": [
        "-y",
        "crawlio-browser"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-08-05 - young repo, little track record yet

license Apache-2.0 - declared in the repository

npm package crawlio-browser - unscoped; check the name against the project README before installing

registry vendor namespace app.crawlio - domain-verified with the official MCP registry

03 · What Crawlio Browser can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Limitations (from the README)

[!WARNING] This is the trade-off, stated plainly: connecting your own Chrome is the feature, and it means an AI agent can act as you on every site you are logged into. It attaches Chrome's debugger to the tab you connect, so it can read cookies, storage, and page content for that session. Review what you connect it to. Prefer a dedicated Chrome profile for agent work. Nothing is

Latest releases

v1.11.0 · 2026-08-10

[1.11.0] - 2026-08-09 · Crawlio can now keep explicitly started training and monitoring inside the Chrome extension while · the MCP server is disconnected. This release also makes the shipped tool, permission, skill…

v1.9.5 · 2026-08-06

Clicking, typing and dragging on a tab the user is not looking at did nothing at all. This · release makes background operation actually work. · The defect · connect_tab({background: true}) correctly declined to steal…

v1.9.4 · 2026-08-06

A click on an element below the fold reported success and did nothing. This release fixes that, · and adds the harness that found it. · The defect · prepareElementForInteraction scrolled only when isElementVisible said…

04 · Who maintains Crawlio Browser

crawlio-browser is maintained by crawlio-app. It's the only MCP server we track from this author; the repo dates to Aug 2026.

05 · Facts

repository: github.com/crawlio-app/crawlio-browser
website: https://www.crawlio.app/browser-agent
category: browser automation - ranked #49 of 196 actively-maintained browser automation servers as of 2026-08-25.
release cadence: 6 releases in the last 90 days (latest 2026-08-10)
registry: app.crawlio/crawlio-browser (active, first published 2026-08-07 · 2 versions)
packages: npm:crawlio-browser

06 · Crawlio Browser FAQ

What is Crawlio Browser?

Is Crawlio Browser still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-10 and it shipped 6 releases in the last 90 days. We re-verify nightly.

How do I install Crawlio Browser?

Run `npx -y crawlio-browser`. You can also paste the ready-made client config above.

Does Crawlio Browser run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Crawlio Browser

Alternatives to Crawlio Browser

Maintained browser automation servers if Crawlio Browser isn't the fit.

Pairs well with

Servers that cover what Crawlio Browser doesn't - only shown when the pairing reason fits the companion.

More browser automation MCP servers · Peek · Pagebolt · Chromium Bridge · UI Debugger MCP · Swell MCP

More TypeScript MCP servers · Creator DB · Mediagen · Cristianoaredes MCP Dadosbr · 2D Assets MCP · Crypto Cult Curt Appfolio MCP Server · see all