Agentic Browser MCP Server

Name: Agentic Browser MCP Server
Author: davarion-tech

@davarion-tech

基本情報

カテゴリ

ブラウザ自動化

ライセンス

MIT

トランスポート

stdio

認証方式

none

作者

davarion-tech

投稿者

DavarionOskr

Agentic Browser MCP Server について

Browser automation for an AI agent using a real Chrome session and human handoff for authentication challenges.

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

**Main perception.** Visible elements with ref, role, name, state and center `@x,y`. `diff: true` returns only changes

Find elements by text anywhere on the page, including off-screen

Pixel → element (role, text, clickable, DOM path), with no image

Where the agent's cursor is and what is under it

Table or repeated list → JSON or CSV rows (title, url, price, image…). `file` saves it to disk

Tokens used this session vs. the screenshot equivalent

Close popups covering the page (close or reject only, never accept). Runs automatically after `browser_navigate`

Several actions in one call, in order, stopping at the first error. Saves one agent turn per action

Hand control to the person watching (login, 2FA, CAPTCHA, a decision) through an on-page banner

Show or hide the cursor, its trail or the live token counter (`hud`)

Last resort: JPEG of the page or of a single `ref`

Browser automation for an AI agent using a real Chrome session and human handoff for authentication challenges.

Follow the project README for installation and MCP client configuration.

browser_snapshot — Main perception. Visible elements with ref, role, name, state and center @x,y. `diff
browser_find — Find elements by text anywhere on the page, including off-screen
browser_element_at — Pixel → element (role, text, clickable, DOM path), with no image
browser_cursor — Where the agent's cursor is and what is under it