Agent Chrome MCP server
Commit 8. Nov. 2026Ermöglicht es AI Agents, mit deinen echten, angemeldeten Chrome-Profilen über Tabs, Klicks, Formulare, Screenshots und Videoaufnahmen zu interagieren.
Auch bekannt als ShadowWalker2014/agentchrome, agentchrome
- Stars
- 1
- Tools
- 16
- Downloads, 30 Tage
- —
- Neueste Version
- 0.1.0
- Letzter Commit
- 8. Nov. 2026
- Lizenz
- MIT
Was ist Agent Chrome MCP?
Agent Chrome ist ein MCP server. Ermöglicht es AI Agents, mit deinen echten, angemeldeten Chrome-Profilen über Tabs, Klicks, Formulare, Screenshots und Videoaufnahmen zu interagieren. Er stellt 16 Tools bereit, etwa tabs_context, tab_groups, navigate.
Zusammenfassung generiert aus dem README des Projekts
Über Agent Chrome MCP server
Agent Chrome verbindet AI Coding Agents mit deinen bestehenden, angemeldeten Google Chrome-Profilen. Dadurch können Agents mit Websites genau so interagieren wie du, indem sie deine aktiven Sessions und angemeldeten Accounts nutzen. Es ist für Entwickler konzipiert, die MCP Clients wie Claude Code, Cursor, Codex, Gemini CLI und andere verwenden. Das System kann lokal auf deinem Rechner oder via Cloudflare laufen und unterstützt das gleichzeitige Verbinden mehrerer Chrome-Profile.
Wenn ein Agent arbeitet, agiert er innerhalb einer eigenen, dedizierten Tab-Gruppe. Du kannst den Fortschritt durch einen blauen Rahmen um die aktive Seite und einen animierten Cursor verfolgen, der den Namen und das Logo des Agents anzeigt. Der Server stellt spezifische Tools für die Browser-Steuerung bereit, einschließlich Navigation, Tab-Management und komplexen Computer-Interaktionen wie Klicken, Tippen und Drag-and-Drop. Er bewältigt zudem schwierige Web-Elemente wie Datei-Uploads und Browser-Dialoge, die automatisierte Agents normalerweise blockieren würden.
Was du damit machen kannst
- 1Automatisierte Web-Interaktion und AufnahmeEin Agent kann eine bestimmte Website ansteuern, einen Screenshot machen und ein Video des Seiteninhalts aufnehmen.
- 2Visuelles Monitoring von Agent-AktionenEntwickler können einem Agent bei der Arbeit in Echtzeit zusehen, mithilfe eines animierten Cursors und eines Status-Pills.
- 3Verwalten mehrerer Browser-ProfileDu kannst verschiedene Chrome-Profile, wie zum Beispiel Arbeits- oder Privat-Accounts, mit demselben MCP server verbinden.
- 4Umgang mit komplexen Web-ElementenDer Server ermöglicht es Agents, mit nativen HTML5 Drag-and-Drop-Funktionen und Datei-Upload-Bereichen zu interagieren.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Agent Chrome MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenAgent Chrome MCP in Claude Code installieren
$ claude mcp add --transport http agentchrome https://agentchrome.dev/mcpAgent Chrome MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"agentchrome": {
"url": "https://agentchrome.dev/mcp"
}
}
}Agent Chrome MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"agentchrome": {
"type": "http",
"url": "https://agentchrome.dev/mcp"
}
}
}Agent Chrome MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"agentchrome","type":"http","url":"https://agentchrome.dev/mcp"}'Agent Chrome MCP in Codex installieren
$ codex mcp add agentchrome --url https://agentchrome.dev/mcpAgent Chrome MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.agentchrome] url = "https://agentchrome.dev/mcp"
Agent Chrome MCP in Gemini CLI installieren
$ gemini mcp add -s user --transport http agentchrome https://agentchrome.dev/mcpAgent Chrome MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"agentchrome": {
"url": "https://agentchrome.dev/mcp",
"type": "http"
}
}
}Agent Chrome MCP tools 16
Erkannt aus dem READMEtabs_contexttab_groupsnavigatecomputerscreenshotread_pagefindform_inputget_page_textjavascript_toolrecordgif_creator
| tabs_context | — | |
| tab_groups | — | |
| navigate | — | |
| computer | — | |
| screenshot | — | |
| read_page | — | |
| find | — | |
| form_input | — | |
| get_page_text | — | |
| javascript_tool | — | |
| record | — | |
| gif_creator | — |
Alle 16 Tools anzeigenWeniger Tools anzeigen
wait_forhandle_dialogresize_windowhistory_search
| wait_for | — | |
| handle_dialog | — | |
| resize_window | — | |
| history_search | — |
Konfiguration
ACM_SERVER
| Name | Beschreibung | Typ |
|---|---|---|
| ACM_SERVER | — |
Automatisierte Checks
Geluften am 13. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarshadowwalker2014/agentchrome is public and reachablegithub.com/shadowwalker2014/agentchrome ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-08github.com/shadowwalker2014/agentchrome ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell16 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeHTTPS endpoint answered 401 (sign-in required)Bestanden
README
Auf GitHub ansehenAgent Chrome is a Chrome extension and an MCP server that let coding agents use your real, signed-in Chrome profiles. It works with Claude Code, Codex, Gemini CLI, Antigravity, Grok, Muse, Cursor, opencode and any other MCP client. Each agent works in its own tab group, and a blue border and an animated cursor show what it is doing. It can take screenshots and record video clips, and you can connect several Chrome profiles at once. The server runs on Cloudflare, or locally on your machine.
If it's useful to you, please star the repo. It helps other people find it.
Install
You need Node.js 18 or newer and Google Chrome.
1. Run the installer
curl -fsSL https://agentchrome.dev/install | sh
On Windows, run this in PowerShell instead:
irm https://agentchrome.dev/install.ps1 | iex
In one pass, the installer:
- Creates your account and saves the key to
~/.config/agentchrome/config.jsonwithchmod 600. - Adds an MCP server named
agentchrometo every agent it finds, in that agent's user-level config (table below). - Writes the
agentchromeskill once, to~/.agents/skills/agentchrome, and symlinks it into each agent's skills folder. - Unpacks the extension to a visible Agent Chrome folder in Documents (
~/Documents/Agent Chromeon macOS and Linux,Documents\Agent Chromeon Windows). - Prints a pairing code and copies it to your clipboard.
To keep everything on your machine with no cloud at all, add --local. See Local mode.
2. Load the extension, once per Chrome profile
The installer opens chrome://extensions and selects the Agent Chrome folder in Finder or File Explorer for you. Keep the folder there: Chrome loads the extension from it.
- In
chrome://extensions, turn on Developer mode. - Drag the Agent Chrome folder onto the page, or click Load unpacked and choose Documents → Agent Chrome. Run
agentchrome extension --pathto print the full path. - Pin Agent Chrome, click it, paste the pairing code and press Connect.
To add another profile (Work, Personal, a client's), switch to that profile, load the same folder, and run agentchrome pair for a new code. Each profile appears as its own browser in list_browsers.
3. Use it
Ask any agent:
Use agentchrome to open news.ycombinator.com, screenshot it, and record a short clip scrolling the front page.
Or let your agent install it
Paste this into Claude Code, Codex or any other coding agent:
Install agentchrome for me by following https://github.com/ShadowWalker2014/agentchrome/blob/main/AGENT_INSTALL.md
The agent runs the installer, then tells you the one step only you can do: loading the extension in Chrome and pasting the code.
Use it from Claude.ai or ChatGPT
The server is a standard remote MCP server with OAuth, so chat apps can use it as a connector. You don't need the command line tool for this.
Claude (claude.ai, Claude Desktop, Cowork): open Customize > Connectors > Add custom connector, enter https://agentchrome.dev/mcp and press Connect.
ChatGPT: turn on Developer mode under Settings > Apps & Connectors > Advanced, then create a connector with the same URL and choose OAuth.
A sign-in page opens. Paste your account key, or press Create an account if you don't have one. Then ask in chat: "Connect my Chrome." The assistant calls pairing_code and walks you through loading the extension and pasting the code.
Where each agent is configured
| Agent | Config written (user level) | Format |
|---|---|---|
| Claude Code | claude mcp add --scope user (~/.claude.json) |
http with an Authorization header |
| Codex | ~/.codex/config.toml |
[mcp_servers.agentchrome] with url and http_headers |
| Gemini CLI | ~/.gemini/settings.json |
httpUrl and headers |
| Antigravity | agy mcp add and ~/.gemini/antigravity/mcp_config.json |
serverUrl and headers |
| Grok | grok mcp add --scope user (~/.grok/config.toml) |
http with a header |
| Muse | ~/.config/muse/settings.json |
type: "streamable-http" |
| Cursor | ~/.cursor/mcp.json |
url and headers |
| opencode | ~/.config/opencode/opencode.json |
type: "remote" |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
serverUrl and headers |
The installer backs up every JSON or TOML file it edits as <file>.bak-agentchrome. The skill is linked into ~/.claude/skills, ~/.codex/skills, ~/.gemini/skills, ~/.gemini/antigravity/global_skills, ~/.cursor/skills and ~/.config/opencode/skills.
Gemini CLI note: Gemini turns off every MCP server in folders you haven't trusted, so
gemini mcp listshows "Disabled" there. Trust the folder with/permissionsinside Gemini, and the server turns on.
Pick agents, or use OAuth instead of a key
agentchrome install claude codex grok # only these agents
agentchrome install --oauth # no secret in config files; each agent signs in through the browser
With OAuth, agents that support MCP sign-in (Claude Code, Codex, Gemini CLI and others) open a sign-in page on first use. Paste your account key once (agentchrome key prints it) and the agent receives short-lived tokens, refreshed for 90 days.
Add it by hand
claude mcp add --scope user --transport http agentchrome https://agentchrome.dev/mcp \
--header "Authorization: Bearer $(agentchrome key)"
codex mcp add agentchrome --url https://agentchrome.dev/mcp --bearer-token-env-var AGENT_CHROME_MCP_KEY
Any MCP client that speaks Streamable HTTP works. Use https://<server>/mcp with a bearer key, or point it at the URL and let OAuth discovery do the rest.
What it does
It also handles the parts of real websites that usually break browser agents:
- Drag and drop works for native HTML5 drag events (Trello-style boards, file drop areas) and for pointer-based sliders and sortable lists.
- File uploads never open the native file picker. The agent can pass real file paths from your computer, or file contents. If a click tries to open the picker, it is held back and the agent is told to fill it.
alert,confirm,promptand "Leave site?" dialogs are reported to the agent instead of freezing it. A navigation the agent asks for leaves an unsaved page and says so.- New tabs opened by a link join the agent's group, and downloads are reported in the result of the click that caused them.
- Pages that fail are explained: HTTP errors such as 404, DNS failures, crashed tabs,
chrome://pages that extensions can't touch, andfile://pages that need permission. - If you press Cancel on Chrome's "started debugging this browser" bar, every agent stops and is told why.
CLI
| Command | What it does |
|---|---|
agentchrome setup [--server URL] [--key KEY] [--local] |
Creates an account or signs in, installs into agents, links the skill, unpacks the extension, prints a pairing code |
agentchrome pair |
Prints a new single-use pairing code, valid for 15 minutes |
agentchrome status |
Shows the account, paired browsers with online state, and which agents are configured |
agentchrome install [ids] [--oauth] / uninstall [ids] |
Adds or removes the MCP server and the skill |
agentchrome revoke <browser-id> |
Removes a paired Chrome profile; it disconnects immediately |
agentchrome rotate-key |
Replaces your account key and rewrites every agent config |
agentchrome key |
Prints your account key |
agentchrome serve [--install] |
Runs the local server; --install starts it at login with launchd |
agentchrome extension [--path] |
Unpacks the extension and shows how to load it |
Tools
The tool names match Claude in Chrome, so prompts and skills written for it work unchanged.
| Tool | What it does |
|---|---|
tabs_context |
Lists this session's tab group and tabs; creates a group with a tab if there is none. all: true lists every tab |
tabs_create / tabs_close / tabs_select |
Opens, closes or switches tabs inside the session group; adopt pulls a user tab into the group |
tab_groups |
Lists, creates, renames, recolors, collapses, moves or ungroups Chrome tab groups |
navigate |
Loads a URL and waits for it; also takes back, forward and reload |
computer |
screenshot, left_click, right_click, middle_click, double_click, triple_click, hover / mouse_move, left_click_drag (HTML5 and pointer drags; start_ref or start_coordinate), type, key (combos like cmd+a), scroll, scroll_to, wait, zoom. Accepts coordinates or element refs, plus modifiers |
screenshot |
Captures the viewport, or with fullPage: true one long image of the whole page. It scrolls through first so lazy images load, and stitches apps that scroll inside a panel, such as Gmail, Notion and dashboards. JPEG or PNG; save: true returns a download link |
read_page |
Returns an accessibility tree with ref_N handles; filter: "interactive", ref_id to read a subtree, viewportOnly |
find |
Finds elements from a plain-language description and returns refs with coordinates |
form_input |
Sets inputs, selects, checkboxes, radios and contenteditable fields by ref |
get_page_text |
Returns the readable text of the article or main content |
javascript_tool |
Runs JavaScript in the page and returns the last expression; supports await and works under strict CSP |
read_console_messages / read_network_requests |
Returns console logs and errors, and requests with status and timing; can include response bodies |
file_upload / upload_image |
Fills a file input or drop zone with local file paths, base64 data, a URL or a screenshot, without the native file picker; leave out ref to fill a picker that a click tried to open |
record |
Records an MP4 or WebM clip of the tab and returns a link. cursor: natural (default, no indicators), agent or hidden; showClicks adds click ripples. action: "scroll" makes a smooth scrolling video of the whole page in one call |
gif_creator |
Records an animated GIF and returns it inline |
wait_for |
Waits until text appears or disappears, a CSS selector matches, or the URL matches |
handle_dialog |
Accepts or dismisses alert, confirm and prompt dialogs |
resize_window |
Resizes the browser window |
history_search |
Searches browsing history, only when you turn it on in the popup |
list_browsers / select_browser |
Lists paired Chrome profiles and picks one; every tool also takes browser: "<name or id>" |
Feature parity
| Claude in Chrome | Codex Chrome extension | agentchrome | |
|---|---|---|---|
| Works with any MCP agent | Claude only | Codex only | yes |
| Tab group per agent session | yes | yes | yes, and the agent can rename and recolor it |
| Several Chrome profiles at once | one connected browser at a time | one profile | yes, all at once |
| Screenshots | yes | yes | yes, including zoom and long full-page images (also inside scrolling panels) |
| Video recording | GIF | no | MP4 or WebM, plus GIF and one-call scrolling videos |
| Console, network, JavaScript | yes | yes | yes |
| Per-site permission prompt | yes | yes | yes, off by default; also a block list |
| Visible "agent at work" indicator | yes | yes | pulsing border, status pill and Stop button |
| Animated agent cursor | no | yes | yes, with the agent's logo; a hand over links |
| Clean recordings without indicators | no | no | yes |
Runs headless from scripts (codex exec, claude -p) |
no | no | yes, since it's a remote MCP server |
| Self-hostable | no | no | yes: Cloudflare or local |
Local mode
curl -fsSL https://agentchrome.dev/install | sh -s -- --local
agentchrome serve --install # starts the local server now and at every login (macOS)
The server listens only on 127.0.0.1:47823 and rejects requests from web pages. In the extension popup, open Server and set it to http://127.0.0.1:47823 before connecting. Screenshots and recordings are saved to ~/.agentchrome/artifacts.
Self-host on Cloudflare
git clone https://github.com/ShadowWalker2014/agentchrome && cd agentchrome
pnpm install
npx wrangler login
sh scripts/deploy-cloudflare.sh my-agentchrome
The script creates a D1 database, a KV namespace and an R2 bucket, runs the migrations, deploys the Worker with its Durable Object, sets a session secret, and prints your own install line (curl -fsSL https://my-agentchrome.<you>.workers.dev/install | sh). After you create your own account, set SIGNUP_MODE to "closed" so nobody else can sign up.
It runs comfortably on the Workers free tier for personal use. Durable Objects hibernate between calls, so an idle extension connection costs nothing.
Security
- Keys: account keys (
acm_sk_…) and device tokens (acm_dt_…) are 256-bit random values. The server stores only their SHA-256 hashes. The local config file ischmod 600. - Pairing: a browser joins your account only with a single-use 10-character code that expires after 15 minutes, created by someone who already holds the account key. Each Chrome profile gets its own device token, which you can revoke on its own.
- OAuth 2.1: PKCE (S256), dynamic client registration, refresh-token rotation and RFC 9728 discovery, using
@cloudflare/workers-oauth-provider. - Isolation: each account has its own Durable Object. MCP session ids are signed with HMAC and bound to the account, so one account cannot use another's session.
- Recordings: screenshots and videos you choose to save go to R2 behind unguessable 144-bit links and are deleted after 7 days.
- Control in the browser: the Stop button on the page or in the popup pauses every agent at once. You can also ask before each new site, block sites, and keep history access off, which is the default.
- Rate limits: sign-up, pairing and the sign-in page are rate-limited per IP address.
- Untrusted pages: the skill and the server instructions tell agents never to follow instructions found inside web pages.
Please report vulnerabilities through a private GitHub security advisory.
How it works
Claude Code ─┐ ┌──────────────────────────────┐ ┌─ Chrome "Work" profile
Codex ───────┤ MCP over HTTPS │ Cloudflare Worker │ WSS │ (extension, paired)
Gemini ──────┼──────────────────► │ /mcp OAuth 2.1 or API key │ ◄────► ├─ Chrome "Personal" profile
Grok, Muse … ┘ │ Durable Object per account │ └─ …
└──────────────────────────────┘
The extension keeps one WebSocket open to the server. The server runs on Cloudflare Workers with one Durable Object per account. Each MCP session gets its own tab group in every paired profile. Tools that act on a page use the Chrome debugger protocol for input, screenshots, console and network logs. A small content script provides element refs, the accessibility tree, the overlay and the agent cursor.
Development
pnpm install
pnpm --filter @agentchrome/server exec wrangler d1 migrations apply agent-chrome-mcp --local
pnpm dev:server # Worker on http://127.0.0.1:8787
node scripts/build-all.mjs # extension, CLI and public assets
pnpm test:e2e # end-to-end tests: real Chromium, the extension and the MCP SDK client
node --test tests/e2e/edge.test.mjs # drag and drop, file pickers, dialogs, new tabs, downloads, errors
ACM_SERVER=https://… pnpm test:e2e # the same suite against a deployed server
sh tests/e2e/local.sh # the same suite against local mode
See AGENTS.md for the architecture and the rules for contributors.
Star history
If agentchrome saves you time, please star it. Stars help other developers find the project.
License
MIT
Agent Chrome MCP Fragen
Wie füge ich Agent Chrome MCP zu Claude Code hinzu?
Führe claude mcp add --transport http agentchrome https://agentchrome.dev/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Agent Chrome MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet Agent Chrome MCP?
Er stellt 16 Tools bereit, darunter tabs_context, tab_groups, navigate, computer, screenshot.
Wie kann ich es mit Claude.ai oder ChatGPT nutzen?
Du kannst es als remote MCP server via OAuth nutzen. Für Claude fügst du die Connector-URL unter Customize > Connectors hinzu, und für ChatGPT erstellst du einen Connector unter Settings > Apps & Connectors.