browser-gateway
Provides structured data extraction and search capabilities for arXiv through bb-browser community site adapters.
Provides structured data extraction and search capabilities for Baidu through bb-browser community site adapters.
Provides structured data extraction and search capabilities for DuckDuckGo through bb-browser community site adapters.
Provides structured data extraction and search capabilities for Google through bb-browser community site adapters.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@browser-gatewayopen example.com and read the page text"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Build-Browser-Gateway
One MCP door to four browser engines.
browser-gateway is a Python MCP server that gives an AI agent a single unified
door to the web, and routes every request to the engine that does that job best:
Intent | Engine | What it does |
| PinchTab | navigate / click / fill / type; snap the accessibility tree, read text or html, eval JS |
| bb-browser | structured data through community site adapters (145 installed on my machine: google, bing, baidu, duckduckgo, arxiv search, and more) |
| Agent Reach | read-only diagnostics only ( |
| Playwright | run a custom Python Playwright script — blocked by default |
There is also a flat tool per engine (browser_pinchtab, browser_bb,
browser_reach, browser_playwright) for callers that already know which hand
they need.
Design rules the agent cannot talk its way around
Hard timeouts everywhere. Every engine subprocess gets a hard timeout; a stuck page can no longer pin the whole MCP session forever.
Explicit truncation. Output is capped by
max_chars(default 10000) and list results bylimit(default 5) — and the caller is always told what was cut. Silent truncation is worse than no truncation.Fail-closed gates. The two risky engines (custom scripts, anything that looks like authentication) are blocked unless two environment variables are deliberately set:
BROWSER_GATEWAY_ALLOW_CUSTOM_SCRIPT=1,BROWSER_GATEWAY_ALLOW_SESSION_AUTH=1.Silent-zero detection. An adapter that returns "success" with zero results is flagged in the output, because an AI agent will otherwise read it as "the answer is that there is nothing there".
Related MCP server: browserpilot
Install
pip install .
# then point your MCP client at:
python -m browser_gateway_mcp.serverEngines are external binaries found on PATH (or via environment variables
below): pinchtab, bb-browser, agent-reach, and a Python interpreter with
playwright installed.
Configuration (environment variables)
Variable | Default | Purpose |
| unset (blocked) | allow the Playwright custom-script engine |
| unset (blocked) | allow the Agent Reach engine |
|
| where screenshot/pdf outputs land |
| unset (stderr only) | optional debug log file |
|
| interpreter used to run Playwright scripts |
| Playwright default | where Playwright browsers are installed |
| command names | engine binary paths |
|
| bb-browser adapter directory |
Notes
Every account, key and password in the published sources is a mock. Real credentials never leave the machine.
The engines themselves are separate open-source tools; what this repository contains is the door, the routing and the safety rules.
Licence
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to fetch, crawl, extract, and search web content through a unified set of tools, with automatic routing to specialized backends.4MIT
- AlicenseNot gradedqualityAmaintenanceEnables agents to control an existing Chromium browser or isolated Playwright profile through 50 tools for reading, interacting with, navigating, capturing, transferring files, and coordinating tabs, with per-site permissions and one-use approvals.5MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents to browse and interact with web pages through a persistent headless Chromium session, serving compact structured orientations, targeted element queries, and full detail only when explicitly requested. It supports navigation, observation, form filling, monitoring, and session management while cutting token overhead by up to ~140x versus raw accessibility-tree dumps.4 npm-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to browse and interact with web pages through a token-efficient, structured page representation — orientation summaries, targeted element queries, and full detail only on request — instead of raw accessibility-tree dumps. Supports navigation, interaction, forms, screenshots, console and network monitoring, session/tab management, and browser-based development auditing.4 npm-