anima-use-google
MCP server that lets AI agents perform Google AI Mode searches using the user's own browser session, returning synthesized answers with citations.
README
<div align=center>
anima-use-google
MCP server + browser sidecar extension that lets AI agents run Google AI Mode searches using your own logged-in browser session, then return the synthesized answer and citations as an MCP tool result.
<img width="256" height="384" alt="AnimAIOS mascot" src="https://github.com/user-attachments/assets/8df6553c-e975-4ac4-b32c-fc73cdf0eebd" />
No headless browser, no stealth tricks, no CAPTCHA fighting. Your real browser profile does the work.
</div>
Quickest path (5 minutes)
You need three things: the MCP server, the native-messaging host, and either the Firefox or Chromium extension. Then wire the server into your agent.
1. Wire the MCP server into your agent
Claude Code:
claude mcp add google-ai-search -- npx anima-use-google
Other agents - add to your MCP config:
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": ["anima-use-google"]
}
}
}
If you do not want your agent to follow npm's moving latest tag, pin the MCP
server to a GitHub commit instead:
claude mcp add google-ai-search -- npm exec --yes --package github:animaios/anima-use-google#<commit-sha> -- anima-use-google
Equivalent MCP config:
{
"mcpServers": {
"google-ai-search": {
"command": "npm",
"args": [
"exec",
"--yes",
"--package",
"github:animaios/anima-use-google#<commit-sha>",
"--",
"anima-use-google"
]
}
}
}
Use a full commit SHA for reproducibility. GitHub installs run the package's
prepare script, so the TypeScript server is built from source before npm runs
the anima-use-google bin.
The MCP server talks to the sidecar over localhost; it does not bundle a browser.
2. Set up a browser sidecar (one-time, non-npm)
The npm tarball ships everything you need. After the first npx anima-use-google, the files live in ~/.npm/_npx/<hash>/node_modules/anima-use-google/ - easiest to clone:
git clone https://github.com/animaios/anima-use-google
cd anima-use-google
Firefox
-
Register the native-messaging host:
node native-host/install-host.cjsThis writes the Firefox native-host registration for your OS:
- Linux:
~/.mozilla/native-messaging-hosts/com.google.ai.search.json - macOS:
~/Library/Application Support/Mozilla/NativeMessagingHosts/com.google.ai.search.json - Windows:
HKCU\Software\Mozilla\NativeMessagingHosts\com.google.ai.search, pointing at%USERPROFILE%\.anima-use-google\com.google.ai.search.json
- Linux:
-
Load the extension in Firefox:
- Open
about:debugging#/runtime/this-firefox. - Click Load Temporary Add-on and pick
extension/manifest.json. - The host process starts on the first search.
- Open
-
Restart Firefox so the new native-messaging host is picked up.
For permanent install (loads on every FF start):
npx web-ext build --source-dir extension --overwrite-dest
# Then sign or load via about:config xpinstall.signatures.required=false (Dev/Nightly)
Chrome / Chromium / Brave
Chromium-based browsers use the extension-chromium/ sidecar. Their native
messaging manifests require allowed_origins, so you need the extension id
before installing the native host.
-
Load the unpacked extension:
- Chrome: open
chrome://extensions. - Chromium: open
chromium://extensions. - Brave: open
brave://extensions. - Enable Developer mode.
- Click Load unpacked and choose
extension-chromium/. - Copy the generated extension id.
- Chrome: open
-
Register the native-messaging host:
# Google Chrome node native-host/install-chrome-host.cjs --browser chrome --extension-id <extension-id> # Chromium node native-host/install-chrome-host.cjs --browser chromium --extension-id <extension-id> # Brave node native-host/install-chrome-host.cjs --browser brave --extension-id <extension-id>The installer writes the manifest or registry entry for your selected browser:
- Chrome on Linux:
~/.config/google-chrome/NativeMessagingHosts/com.google.ai.search.json - Chrome on macOS:
~/Library/Application Support/Google/Chrome/NativeMessagingHosts/com.google.ai.search.json - Chrome on Windows:
HKCU\Software\Google\Chrome\NativeMessagingHosts\com.google.ai.search - Chromium on Linux:
~/.config/chromium/NativeMessagingHosts/com.google.ai.search.json - Chromium on macOS:
~/Library/Application Support/Chromium/NativeMessagingHosts/com.google.ai.search.json - Chromium on Windows:
HKCU\Software\Chromium\NativeMessagingHosts\com.google.ai.search - Brave on Linux:
~/.config/BraveSoftware/Brave-Browser/NativeMessagingHosts/com.google.ai.search.json - Brave on macOS:
~/Library/Application Support/BraveSoftware/Brave-Browser/NativeMessagingHosts/com.google.ai.search.json - Brave on Windows:
HKCU\Software\BraveSoftware\Brave-Browser\NativeMessagingHosts\com.google.ai.search
On Windows, the manifest JSON itself is written under
%USERPROFILE%\.anima-use-google\<browser>\com.google.ai.search.json, and the registry key points the browser at that file. - Chrome on Linux:
-
Reload the extension so
chrome.runtime.connectNative("com.google.ai.search")sees the manifest.
Switching between Firefox and Chromium-based sidecars
The MCP server always connects to the first browser native host listening on
127.0.0.1:51784. When switching browsers during development, make sure the
old sidecar is not still owning that port.
-
Disable or unload the sidecar you are not testing:
- Firefox: remove or disable the temporary add-on from
about:debugging#/runtime/this-firefox. - Chrome/Chromium/Brave: disable or remove the unpacked extension from
chrome://extensions,chromium://extensions, orbrave://extensions.
- Firefox: remove or disable the temporary add-on from
-
Stop any stale native host:
ps -ef | rg '[n]ative-host/host\.js' kill <pid> -
Register the host manifest for the browser you want:
# Firefox node native-host/install-host.cjs # Google Chrome node native-host/install-chrome-host.cjs --browser chrome --extension-id <chrome-extension-id> # Chromium node native-host/install-chrome-host.cjs --browser chromium --extension-id <chrome-extension-id> # Brave node native-host/install-chrome-host.cjs --browser brave --extension-id <brave-extension-id> -
Reload the chosen browser extension so it reconnects to native messaging.
-
Confirm which browser owns the host before running an E2E test:
ps -ef | rg '[n]ative-host/host\.js|[b]rave|[c]hrome|[c]hromium|[f]irefox' ss -ltnp 'sport = :51784'For Chromium-based browsers, the host command should include an origin like
chrome-extension://<extension-id>/. For Firefox, it is normally launched without that Chrome extension-origin argument.
3. Use it
Ask your agent normally:
Search Google AI Mode for: Next.js 15 App Router best practices
The agent calls search_google_ai, your browser sidecar opens the udm=50 search in your profile, the extension parses the AI answer with inline [1][2] citations, and the agent gets a grounded markdown response.
How it works
Agent (stdio) <---> MCP server <---> localhost TCP <---> host.js
<---> browser native port <---> background script
<---> opens google.com/search?udm=50&q=...
<---> content.js parses AI answer + sources
<---> response back along the same chain
Your logged-in Google cookies are reused because the tab is opened in your own browser profile - if you have AI Mode enabled, it works; CAPTCHAs don't trigger (real user profile, no stealth games).
The multilanguage completion detection (SVG thumbs-up → aria-label → text markers → 40s fallback) and SERPO-style citation parsing are ported from the Battle-tested google-ai-mode-mcp.
Developers
Want to hack on the MCP server or build from source:
npm install
npm run build # tsc -> dist/
npm test # node:test regression suite
npm link # then `anima-use-google` on PATH
Project layout:
src/+dist/- TypeScript MCP server publishing asanima-use-google.native-host/-host.jsbridges browser native messaging <-> localhost TCP;install-host.cjswrites the Firefox manifest;install-chrome-host.cjswrites the Chrome/Chromium/Brave manifest.extension/- Firefox MV3 sidecar.extension-chromium/- Chrome/Chromium/Brave MV3 sidecar using a service worker background.- Selector constants live in each extension's
src/selectors.js- update both if Google's AI Mode DOM shifts.
Tuning
Cutoff markers (end-of-answer disclaimers, language-aware) and citation selectors are in extension/src/selectors.js and extension-chromium/src/selectors.js. If extraction fails on your locale, add your language's markers there.
License
unLICENSE. See LICENSE.
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。