YetiBrowser MCP
An open-source alternative to BrowserMCP that enables AI assistants to interact with web pages through a Chrome extension. Provides browser automation capabilities without closed-source dependencies by bridging MCP clients to active Chrome tabs.
README
YetiBrowser MCP
YetiBrowser MCP is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or your own tools—can automate a real browser tab while keeping every byte on your machine and auditable.
Why pick YetiBrowser MCP?
- Transparent and hackable – no blob downloads. Inspect, fork, and extend every component.
- Local-first – the extension talks only to a localhost MCP server; browsing data never leaves your device.
- Cross-browser – shared logic powers both Chrome and Firefox packages.
- Developer-focused tooling – richer console capture, DOM diffing, page-state dumps, and full-page screenshots built for debugging and QA.
- Production-friendly – scripts and docs for packaging, publishing, and integrating with IDE workflows.
Repository layout
packages/shared– shared TypeScript definitions for messages and tool schemas.packages/server– the MCP server that bridges MCP clients to a running browser tab.extensions/shared– shared extension source (background/popup) and assets.extensions/chrome/extensions/firefox– per-browser packaging layers.docs/– workspace commands, publishing checklists, and feature notes.scripts/– helper utilities such aspackage-extensions.shfor release zips.
MCP Tools Available
browser_snapshot– capture an accessibility-oriented snapshot of the current pagebrowser_snapshot_diff– compare the two most recent snapshots to highlight DOM/ARIA changesbrowser_navigate– load a new URL in the connected tab and return an updated snapshotbrowser_go_back/browser_go_forward– move through history while keeping MCP in syncbrowser_wait– pause automation for a set number of secondsbrowser_press_key– simulate a keyboard key press on the focused elementbrowser_click– click the element identified by a CSS selectorbrowser_hover– hover the pointer over the targeted elementbrowser_type– type text (optionally submitting with Enter) into an editable elementbrowser_select_option– choose one or more options in a<select>elementbrowser_screenshot– capture a viewport or full-page screenshot via the DevTools protocolbrowser_get_console_logs– return recent console output, including errors with stack tracesbrowser_page_state– dump forms, storage keys, and cookies for the connected page
MCP Server Installation
Codex CLI
- Edit your ~/.codex/config.toml and add the MCP entry:
[mcp_servers.yetibrowser-mcp] command = "npx" args = ["yetibrowser-mcp", "--ws-port", "9010"] - Restart
codexCLI command; you should seeyetibrowser-mcplisting under/mcptools.
Claude Code
- Make sure the extension is installed and connected to a tab, then start the MCP server with
npx yetibrowser-mcp --ws-port 9010(or run the locally built CLI). - Add the server entry to
~/Library/Application Support/Claude/claude_desktop_config.json(see the example indocs/publishing.md). - Restart
claudeso it picks up the new MCP server; you should seeyetibrowser-mcplisted under the/mcptools menu once the extension connects.
Other MCP-aware clients
- Any MCP client can connect by spawning the CLI (
npx yetibrowser-mcp --ws-port 9010) and pointing it at the Chrome extension port. - The server exposes the standard MCP transport over stdio, so use whatever configuration mechanism your client supports to run the command above when a tab is connected.
MCP Inspector
- For testing and debugging outside a coding agent.
npx @modelcontextprotocol/inspector yetibrowser-mcp -- --ws-port 9010to run and inspect the MCP server in conjunction with the YetiBrowser MCP browser extension.
Troubleshooting
- If you get a connection error, check to make sure you don't have another instance of the server running on the same port. Default is port
9010.
Documentation & build scripts
- Workspace commands live in
docs/workspace-commands.md. - Publishing steps (npm + extension stores) are in
docs/publishing.md. - Screenshot behaviour is documented in
docs/screenshot.md. - Generate distributable Chrome/Firefox zips with
./scripts/package-extensions.sh(outputs toartifacts/). - A repository-level privacy policy is available in
PRIVACY.md.
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。