Skip to main content
Glama

NexusBrowser

Release PyPI Tests License: MIT Chrome MV3 Python 3.14 MCP

NexusBrowser: your real Chrome, driven by an AI agent in a background tab.

NexusBrowser: an AI agent types into a form, picks an option and clicks in a background Chrome tab while the user keeps browsing

Your real Chrome, driven by AI agents in background tabs. NexusBrowser lets Antigravity, Claude and Codex use the user's own Chrome (their sessions, their extensions) through one shared local bridge and one MCP server, nexus-browser. Each agent works in its own background tabs, grouped under its name, with real (trusted) mouse and keyboard events sent through the Chrome DevTools Protocol, while the user keeps working in their own tabs.

Version 2.9.0 · Windows 10/11 · Chrome 116+ · Python 3.14 · MIT licence

Part of the Nexus family: NexusWindows (Claude · Codex · Antigravity), NexusBrowser (repo), NexusAndroid (repo). Project page: julienpiron.fr/nexusbrowser.

Why

Browser automation usually means a separate headless browser (no sessions, no extensions) or screen-level computer use that moves the user's cursor and brings the window to the front. NexusBrowser works inside the browser the user already uses, without activating the agent's tab or window, and keeps the guard rails in the extension and the bridge rather than in the agent: tab ownership, an allowlist of DevTools commands, masked secrets, an emergency stop.

  • Antigravity: its own browser agent runs in a separate Chrome profile, without the cookies or sign-ins of the user's browsing (Antigravity docs). NexusBrowser gives it the user's real Chrome.

  • Claude and Codex already have their own Chrome extension (Claude in Chrome, the Codex Chrome extension). NexusBrowser complements it where a bridge with the DevTools protocol helps: JavaScript dialogs (browser_handle_dialog), detailed network capture with response bodies, elements inside cross-origin iframes, content and Google Docs/Sheets/Slides exports, and downloads.

Until 2.4.0 it was published here as "Antigravity Browser Bridge", for Antigravity only. Since 2.6.0 it is a neutral bridge shared by several agents.

Related MCP server: tobkiri-tabs

Pieces

Folder

Role

extension/

Chrome MV3 extension "Nexus Browser Bridge": CDP actions, locators, network, dialogs, cross-origin iframes, exports, tab ownership, control panel

native-host/

Local bridge (bridge_server.py: WebSocket 9224 for the extension, HTTP 9225 for the agents) and native host com.nexus.browser_auth

client/

MCP server nexus-browser (mcp_server.py), authenticated transport (bridge_client.py), CLI (browser_cli.py), shared emergency stop

skills/, plugins/

Skill (copied for Antigravity, Claude Code and Codex) and Antigravity plugin, by install.ps1

Tools

47 MCP tools. Tool descriptions and messages are in French; tool and parameter names are in English.

Area

Tools

Tabs

browser_list_tabs, browser_active_tab (read only), browser_new_tab, browser_select_tab, browser_adopt_tab, browser_release_tab, browser_group_tabs, browser_close_tab, browser_reload, browser_navigate, browser_wait_load

Input (trusted CDP events)

browser_click, browser_semantic_click, browser_hover, browser_fill, browser_semantic_fill, browser_select_option, browser_check, browser_press_key, browser_type_keys, browser_drag_and_drop, browser_scroll, browser_upload, browser_handle_dialog

Finding elements

browser_find (Playwright-style locators: role, label, text, placeholder, test id, in every frame), browser_interactive_map, browser_vision_inspect and browser_click_mark (Set-of-Mark badges), browser_axtree, browser_content, browser_check_handoff (2FA, CAPTCHA)

Network and downloads

browser_network_record, browser_network_stop, browser_network_requests, browser_network_response, browser_wait_network_idle, browser_download_status, browser_wait_download, browser_get_cookies

Output

browser_screenshot, browser_pdf, browser_export (main content as Markdown, text or HTML), browser_export_gsuite (Google Docs, Sheets, Slides through Google's export URLs), browser_export_youtube_transcript, browser_logs

Page access

browser_eval, browser_cdp_send (allowlisted commands)

Install

Requirements: Windows 10 or 11, Chrome, uv, Python 3.14.

git clone https://github.com/pironjulien/NexusBrowser.git
cd NexusBrowser
pwsh -NoProfile -File install.ps1
  • Python environment, token, logs, screenshots and exports live in ~\.nexus\nexus-browser (outside the clone).

  • Scheduled task Nexus Browser Bridge with no trigger: the bridge starts on demand (first agent call, schtasks /Run).

  • Native host com.nexus.browser_auth declared to Chrome (HKCU): it computes the extension's proofs, the token never reaches Chrome.

  • MCP server nexus-browser registered for Claude Code, Codex and Antigravity when they are installed, each with NEXUS_BROWSER_AGENT set to its name (default tab group).

  • When the bridge has to relaunch Chrome, it uses the Default profile; extra Chrome flags (language...) can be added with the NEXUS_CHROME_EXTRA_ARGS environment variable (allowlist: --lang, --accept-lang, --variations-override-country, --disable-features=Glic…, --force-dark-mode; anything else is ignored).

  • Migration from the former "Antigravity Browser Bridge": its task (same ports) and native host com.nexusagy.bridge_auth are removed.

Then load extension\ once in chrome://extensions (developer mode, "Load unpacked") and remove the old "Antigravity Browser Bridge" if present. The extension ID is fixed by the public key in manifest.json (blcgddmjdkobmgakjffjpgiicjlflgjf), the same on every PC and whatever the folder; it is the only origin the bridge and the native host accept.

The MCP server from PyPI

Once the bridge and the extension are installed (above), any MCP client can also start the server straight from PyPI, without the clone:

claude mcp add nexus-browser --scope user -e NEXUS_BROWSER_AGENT=Claude -- uvx nexus-browser

Without the bridge, the server still starts and lists its 47 tools, and every call answers with a clear error that points to the one-time install.

Security (held by the extension and the bridge, not by the agent)

  • Mutually authenticated bridge (nexus-browser/1): HMAC proofs over both nonces, then every message signed with a per-connection key and a strict sequence number. HTTP requires X-Nexus-Browser-Token and refuses any browser origin.

  • Tab ownership: every bridge client identifies itself (agent + session headers, forwarded by the bridge in the signed channel). A tab opened by browser_new_tab belongs to that session (chrome.storage.session); any page command on another tab (the user's, another agent's) is refused. A tab of the user only through browser_adopt_tab(tab_id, julien_asked=True) (the parameter keeps its historical name). tab_id is mandatory on every page tool. A session whose MCP process is gone (or silent for 1.618 x 60 s; servers beat every 37 s) leaves orphan tabs: the same agent can reclaim (browser_adopt_tab, also automatically at startup), close or release them; never another agent.

  • CDP allowlist for browser_cdp_send; every extension script runs in an isolated world (only browser_eval, the YouTube transcript and browser_cdp_send(..., world="page") touch the page's world).

  • Secrets: secret headers, URL parameters and JSON/form body fields masked (pagination tokens and LLM token counters kept); cookie values only for local development origins (include_values=True); uploads refused by the bridge itself from secret folders (normalized paths). The value of a password, one-time code or payment card field (type=password, autocomplete current-password, new-password, one-time-code, cc-number, cc-csc, cc-exp) never leaves the page: browser_content (html mode included), browser_vision_inspect, browser_find, browser_axtree and the value read back by browser_fill return [valeur masquée] instead.

  • browser_eval is full access to the page, nothing masked: like browser_cdp_send(Runtime.evaluate) (both worlds share the document), it reads what the page reads (non-HttpOnly cookies through document.cookie, localStorage, sessionStorage, IndexedDB, form fields) and its fetch carries the user's session. The masking above covers the dedicated tools, not scripts nor the raw Chrome replies of browser_cdp_send (DOM.getOuterHTML, Accessibility.getFullAXTree...): kept on purpose, said plainly in the tool, the skill and the server instructions. Page.reload with scriptToEvaluateOnLoad is refused (script injected at load).

  • Emergency stop (Ctrl+Alt+Shift+Esc, STOP button of the control panel, ~\.nexus\stop): commands already running are cancelled (typing, drag, waits), debuggers detached, every action refused for 120 s. The same file protocol is shared with the NexusWindows agents.

  • Control panel (side panel, Alt+Shift+N): tabs driven by each agent, debugger state, STOP, give a tab back.

  • Whoever holds the bridge token controls the browser session: keep ~\.nexus\nexus-browser\bridge-token private.

Checks

pwsh -NoProfile -File test.ps1         # offline: ruff, Pyright, pytest (real bridge on ephemeral ports), Node tests
pwsh -NoProfile -File test.ps1 -Full   # plus real validation in the user's Chrome: --mouse then --full-live
pwsh -NoProfile -File verify.ps1 -Browser  # task, native host, bridge reached, loaded extension up to date

test.ps1 uses the environment created by install.ps1.

Privacy

NexusBrowser runs entirely on your PC: a Chrome extension, a local bridge bound to 127.0.0.1 (authenticated by a local token) and an MCP server. It has no account, no telemetry, no analytics and no remote server; nothing is sent to the author or to any third party.

  • What it reads: in the tabs the agent opened (or a tab of yours you explicitly let it adopt): page text and accessibility tree, screenshots, console logs, network requests (headers and secret fields masked), cookies when browser_get_cookies is called. Password, code and card values are masked in reads and drawn as dots in screenshots and PDFs (every frame, cross-origin ones included); console logs are masked like network bodies; browser_eval and Runtime.evaluate through browser_cdp_send do have full access to the page.

  • Network: pages are loaded by your own Chrome with your own sessions, as if you browsed them. Exports (Google Docs, Sheets, Slides, YouTube transcripts) are fetched from those sites in your session.

  • Where it goes: tool results are returned to the AI client you connected (Antigravity, Claude, Codex…), which may send them to its model provider under its own privacy policy.

  • What it stores, under ~/.nexus/nexus-browser/: the Python environment, the bridge token, bridge.log (connection and emergency-stop events, rotated at 1 MB, three backups), install.log, screenshots (at most 50, each kept under 24 hours) and the exports you ask for. The extension keeps tab ownership in Chrome's session storage, cleared when Chrome closes.

  • Removing it: remove the extension from Chrome, delete the scheduled task Nexus Browser Bridge and the registry key HKCU\Software\Google\Chrome\NativeMessagingHosts\com.nexus.browser_auth, then delete ~/.nexus/nexus-browser/.

Questions or concerns: open an issue on this repository.

Limits

  • Windows and Chrome only (Manifest V3, chrome.debugger). While the debugger is attached, Chrome shows its "is being debugged" banner on the agent tab. Protected pages (chrome://, the Web Store) cannot be scripted.

  • Tab ownership is per MCP process: sub-agents of one conversation share it.

  • The YouTube transcript reads the page's own player (page world).

  • Tool descriptions, messages and code comments are in French.

Licence

MIT, see LICENSE. Copyright (c) 2026 Julien Piron.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Enables AI agents to drive the user's already-running Google Chrome through a WebSocket bridge, listing and switching tabs, navigating, clicking, typing, scrolling, extracting DOM, taking screenshots, and evaluating JavaScript. It works without restarting Chrome and preserves all existing logins, cookies, and 2FA sessions.
    11
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to create, read, and operate granted background tabs in Chrome via a local stdio MCP server, preserving the human's front tab. Supports tab groups, navigation, clicking/typing, screenshots, and human-priority permissions.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to control Chrome, Edge, Brave and other Chromium browsers through an extension and native messaging host, exposing a Claude-in-Chrome-compatible tool set for real clicks, typing, screenshots, accessibility-tree reading, page text, form filling, JavaScript execution, console and network inspection, file uploads and GIF recording. Agent sessions run in isolated tab groups with per-site permission prompts, activity logging and a global stop control.
    Apache 2.0