TabDeck
Provides a web search tool that opens a background Google search tab, returns up to 10 results with title, URL, and snippet, and falls back to Bing if Google shows a captcha or no results.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TabDeck lets a local AI agent drive your real, logged-in Chrome over MCP, with every task kept in its own named tab group. A small Chrome extension plus a zero-dependency MCP server; works with Claude Code, Codex, Copilot CLI, Cursor or any other MCP client.
Inspired byClaude in Chrome. TabDeck is an independent, model-agnostic take on the same idea. It is not affiliated with Anthropic and shares no code with that extension.
✨ Why
Your logged-in Chrome | No prompt per connection | Any model / client | Tidy agent tabs | |
Remote-debugging MCPs | ✅ | ❌ | ✅ | ❌ |
Extension-relay MCPs | ✅ | ✅ | ✅ | ⚠️ |
Claude in Chrome | ✅ | ✅ | ❌ | ✅ |
TabDeck | ✅ | ✅ | ✅ | ✅ |
🗂️ One tab group per session, named after the task, in a color that stands apart.
🧲 Tabs opened by a click stay in the group and never steal the tab you are looking at.
🌙 Works in background tabs: clicking, typing and screenshots need no focus.
🔒 Only touches its own tabs, unless it explicitly adopts one of yours.
🚫 No "Open the app?" prompts: pages cannot launch desktop apps (
msteams:,zoommtg:,slack:,mailto:...), so the agent stays in the web version and nobody has to click a browser prompt.🔍 Debugging built in: console, network, dialogs, iframes and file uploads.
🪶 No dependencies: about 1,700 lines of plain JavaScript.
Related MCP server: byob
🎬 Demo
Images on this page are illustrations, not captures of a real browser.
🚀 Install
Chrome 116+, Node.js 18+, Windows only for now.
git clone https://github.com/shaojunying/tabdeck.git
cd tabdeck
node scripts/setup.mjsOpen
chrome://extensions, turn on Developer mode, Load unpacked, chooseextension/.Add the stdio server to your MCP client:
{ "mcpServers": { "tabdeck": { "command": "node", "args": ["C:\\path\\to\\tabdeck\\src\\mcp-server.js"] } } }Claude Code:
claude mcp add tabdeck -- node C:\path\to\tabdeck\src\mcp-server.js
Uninstall with node scripts/setup.mjs --uninstall, then remove the extension.
🧰 Tools
Tool | What it does |
| Name this session's tab group after the task |
| List this session's tabs, or everything with |
| Open a tab in the group, in the background by default |
| Take over existing tabs by moving them into the group |
| Close tabs; only the session's own unless |
| Switch to a tab |
| General tab organising |
| Rename, recolor, collapse or expand a group |
| Close everything, dissolve the group, or keep it |
Tool | What it does |
| Load a URL and wait for it |
| Read the page, iframes included, as a compact accessibility tree with element refs |
| Click by ref; reports tabs the click opened |
| Type into a field by ref, optional Enter |
| Press a key |
| Choose options in a native |
| Fill several fields in one call: text, selects, checkboxes |
| Choose local files in a file input |
| Accept or dismiss an alert, confirm or prompt |
| Hover an element |
| Scroll by a screen, to top / bottom, or to an element |
| Back, forward, reload |
| Wait for text to appear or disappear |
| Run a JavaScript expression in the page |
| JPEG of the visible area, at most 1280px wide |
| Console output and uncaught errors, including earlier ones |
| Requests the tab made; headers and bodies for one request |
Tool | What it does |
| Search the web with no API key: opens a background tab on Google (Bing if Google shows a captcha or nothing), returns title, URL and snippet for up to 10 results, then closes the tab |
🧩 How it works
flowchart LR
A["MCP client"] -- stdio --> B["mcp-server.js<br/>one process = one session"]
B -- named pipe --> C["host.js"]
C -- native messaging --> D["extension"]
D -- "tabs · tabGroups · debugger" --> E["Chrome"]Page actions use chrome.debugger, so Chrome shows its "started debugging this browser" bar while a session is acting on a page.
🛡️ Limits and security
The agent has the same access to a page as you, including your logins. Use it only with agents and prompts you trust; web pages can contain text written to mislead an agent.
Not yet: macOS / Linux, per-site allowlist, screen recording.
page_networkonly sees requests made after TabDeck first acted on the tab, and redacts cookie and authorization headers.page_uploadrefuses files that look like credentials or keys. This is a guard against slips, not a security boundary.page_evalruns arbitrary JavaScript in session tabs.web_searchreads the search engine's result page, so it runs as you (your region, language and account) and can break when that page's markup changes. Many searches in quick succession can trigger a captcha;npm run test:searchchecks it against the live sites.chrome://pages and the Chrome Web Store cannot be driven.
node test/plumbing.test.mjstests the server and host without Chrome;npm run test:liveruns against your real Chrome with temporary tabs.node scripts/reload.mjsreloads the extension after you changeextension/, with no Chrome prompt.Cannot reach the TabDeck extension: Chrome is not running, the extension is not loaded, or setup has not been run.Specified native messaging host not found: you ran setup from a shell inside a packaged (MSIX) app, which writes to a private registry view. Rerun it with--via-wmi.Logs:
native-host/host.log, and the "service worker" link on the TabDeck card inchrome://extensions.
📄 License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI agents drive the real, already-logged-in Chrome browser through a companion extension, navigating tabs, clicking, typing, reading pages, filling forms, taking screenshots, and inspecting cookies, storage, console and network traffic. It keeps all communication on the local machine, with no remote-debugging port to expose and no separate headless browser or manual cookie copying to set up.1 npmISC
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI coding assistants drive the user's own already-signed-in Chrome, so agents can read logged-in pages, click, fill forms, navigate, screenshot, inspect network traffic and storage, and run multi-step browser workflows without a separate headless browser or remote debugging port. All communication stays on the user's machine and agent-opened tabs are grouped so they never steal focus.1 npmISC
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI assistants drive your real, already-logged-in Chrome through a browser extension, so agents can read, click, type, navigate, screenshot, inspect network traffic, and manage cookies or storage on pages that require existing sessions. It works without opening a remote-debugging port and keeps all communication on your machine.1 npmISC
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI coding tools drive the user's actual, already-logged-in Chrome browser — snapshotting pages, clicking, typing, navigating, reading content, taking screenshots, and inspecting cookies, network traffic, and console output. Browser automation happens through a Chrome extension using Native Messaging, so no remote-debugging port is exposed and all communication stays on the local machine.1 npmISC