chromiumfish_mcp
Enables MCP clients to control a ChromiumFish browser for web automation, including page management, navigation, interaction, and content extraction.
README
chromiumfish_mcp
chromiumfish_mcp is an independent Model Context Protocol (MCP) server for ChromiumFish. It lets Claude Code, Claude Desktop, Cursor, and other MCP clients drive a ChromiumFish browser through structured tools.
It uses the official ChromiumFish npm package and ships no Chromium source or binaries — on the first tool call that needs a page, the upstream SDK downloads and caches the matching browser build. See docs/USAGE.md for detailed tool usage.
Requirements
- Node.js 20 or later.
- An OS and architecture supported by ChromiumFish.
- Network access for the initial browser download. If no prebuilt asset matches your platform, build ChromiumFish locally and point to it with
--chrome-pathorCHROME_BIN.
Install
npm install --global github:LowOrbitLab/chromiumfish_mcp
chromiumfish_mcp --persona-seed alice
Or run without installing: npx --yes github:LowOrbitLab/chromiumfish_mcp --persona-seed alice.
Configure
Add the server to your MCP client config:
{
"mcpServers": {
"chromiumfish": {
"command": "chromiumfish_mcp",
"args": ["--persona-seed", "alice"]
}
}
}
To run from GitHub instead of a global install, set "command": "npx" and prepend "--yes", "github:LowOrbitLab/chromiumfish_mcp" to args. On Windows, use npx.cmd if your client cannot resolve npx.
Tools
| Tool | Purpose |
|---|---|
list_pages, open_page, select_page, close_page |
Manage pages by stable pageId |
navigate, navigate_back, navigate_forward, reload |
Navigate and use page history |
snapshot |
List visible interactive elements with e1/e2 references |
get_text, take_screenshot |
Retrieve page or frame content |
click, hover, type_text, select_option, set_checked, press_key, scroll, wait_for |
Interact with the page |
click_at |
Click absolute coordinates (for widgets snapshot cannot see) |
list_frames |
List frames/iframes with stable IDs |
find_challenge, solve_challenge |
Detect and clear interstitial / framed challenges |
evaluate |
Run arbitrary JavaScript — requires --allow-eval |
run_task |
Native ChromiumFish agent — requires --allow-native-agent |
Snapshot references, frame-aware interaction, waiting, and the cross-origin challenge workflow are covered in docs/USAGE.md.
Command-line options
--persona-seed VALUE Use a stable browser fingerprint persona
--chrome-path PATH Use a local ChromiumFish executable
--browser-version VERSION Select an upstream ChromiumFish build version
--headed Show the browser window
--window-size WIDTHxHEIGHT Set the browser window size
--timezone ZONE Use an IANA time zone or auto
--proxy URL Route browser traffic through a proxy
--allowed-host HOST Allow top-level navigation to a host and its subdomains; repeatable
--max-text-chars N Set the hard limit for text and snapshot output
--allow-eval Enable arbitrary JavaScript execution
--allow-native-agent Enable the native ChromiumFish browser agent
Proxy credentials can be embedded in the proxy URL, but are then exposed in the client config. Never commit config files containing proxy passwords, cookies, or API keys.
Security
- stdio only — do not expose the Chromium DevTools endpoint to the public internet.
evaluateand the native agent are disabled by default; enable them only in trusted environments.--allowed-host example.comrestricts top-level HTTP/HTTPS navigation (redirects, links, form posts, popups) to a host and its subdomains. Third-party subframes and page assets remain reachable — it is a navigation guard, not a network egress filter.- Clients can click and type with real side effects. Keep human confirmation for purchases, publishing, deletion, and permission changes.
- Each process runs an independent browser context; this is not a shared multi-tenant service.
Development
npm ci
npm test
node dist/index.js --help
The suite uses an in-memory MCP transport to verify tool discovery, dangerous-tool opt-in, and results. It does not download or launch a browser.
License
MIT. ChromiumFish code and trademarks belong to their respective contributors; see NOTICE for attribution. This is an independent wrapper, not an official ChromiumFish release.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。