chrome-mcp

Let Claude use the Chrome you are already logged into. Not a fresh automated browser that greets every site as a stranger — your Chrome, with your sessions, your cookies, your 2FA already done. If you can see a page in your browser, your agent can read it, without logging in again and without pasting credentials anywhere.

Most browser MCP servers launch their own Chromium and hand your agent a signed-out window. chrome-mcp does the opposite: an MV3 extension dials into a localhost WebSocket server and drives the browser you already have open, through chrome.scripting/chrome.tabs. Works with Claude Code, Claude Desktop, and any other MCP host.

Distributed as an npx CLI (the MCP server) plus an extension, from the Chrome Web Store or loaded unpacked.

This build is extension-only. It never launches or attaches a Chromium of its own, so the extension is required, not optional — without it, no tool can run. The CDP flags (--cdp-fallback, --no-cdp-fallback, --cdp-endpoint, --prefer) are still accepted for back-compat but are ignored.

Full design: docs/BLUEPRINT.md — architecture, wire protocol, the complete tool surface, the extension manifest, the security model, and the phased build plan.

Use Claude in your signed-in Chrome

You are already signed in to Gmail, GitHub, your analytics dashboards, the admin panel, the CRM. chrome-mcp lets Claude (Claude Code, Claude Desktop, or any other MCP host) work in those same tabs: no re-login, no second 2FA prompt, no password or cookie in a config file. The extension runs inside your normal Chrome, so a page the agent opens is the page you would see.

• Gmail — read a thread or search results in a tab you already have open.
• GitHub — go through PRs, issues and settings pages as yourself, private repositories included.
• Dashboards — pull numbers from analytics, billing or admin screens that have no API, or whose API you never set up.

Other tools drive a signed-in Chrome too (the hangwin/mcp-chrome extension, for one), so the question is what you get on top of the session:

• A per-domain allowlist, deny-all by default. With no flags the agent can read nothing. --allow-domain mail.google.com --allow-domain github.com opens exactly those hosts (*.example.com covers a domain and its subdomains); every other site is refused before the call reaches the page. Reads are gated, not only clicks, and the extension re-checks the same policy on its side. Mutations, eval, downloads and uploads are separate opt-ins.
• Password values are never returned, and --redact scrubs tokens, API keys and JWTs out of page reads.
• An audit trail: every call is logged with the URL, the allow/deny verdict, duration and bytes returned.
• Background tabs and batch: open pages with active: false and read many at once in one call, without stealing focus from the tab you are working in.
• Several Chrome profiles: load the extension in your work and personal profiles and switch between them with profile_use.
• auth_check: when a session does expire, the agent gets an [AUTH_REQUIRED] signal instead of a confusing timeout, so it can stop and ask you to sign in again. chrome-mcp never holds credentials or signs in for you.

Setup is two pieces: the MCP server (npx, below) and the extension, which you can install from the Chrome Web Store or load from the folder the server unpacks.

Quickstart

Up and running in one paste

Hand this to your AI agent (Claude Code, Cursor, Windsurf, anything MCP) and it installs the server, wires it into the client, and walks you through the two steps that must happen inside Chrome:

Set up chrome-mcp on this machine by fetching and following
https://raw.githubusercontent.com/Mehmoodqureshi/chrome-mcp/main/SETUP.md
exactly, step by step. Work autonomously and verify each step.

Prefer to read before you run an agent on your machine? SETUP.md is the exact file the agent follows. The manual steps are below.

1. Register the MCP server with your host.

claude mcp add chrome-mcp -s user -- \
  npx -y @mehmoodqureshi/chrome-mcp \
  --allow-domain example.com --enable-mutations --persist-token

{
  "mcpServers": {
    "chrome-mcp": {
      "command": "npx",
      "args": ["-y", "@mehmoodqureshi/chrome-mcp",
               "--allow-domain", "example.com", "--enable-mutations",
               "--persist-token"]
    }
  }
}

By default everything is deny-all (no domains, no eval, no mutations). Grant exactly what you need with --allow-domain <glob> (repeatable), --enable-mutations, --enable-downloads, --enable-uploads, --unsafe-enable-eval, or --unsafe-all-domains.

--enable-uploads permits upload_file (setting local file(s) on a page's file <input>). It is off by default because sending local files to a page is an exfiltration risk; it is also gated by the destination-domain allowlist. Pair it with --uploads-dir <path> to restrict uploads to files inside that directory (.. traversal is blocked) — strongly recommended for unattended use.

Pair once, never again. Both examples above include --persist-token, which is what makes the pairing survive a restart — drop it if you'd rather have the stricter default described next.

Without --persist-token a fresh token is minted every boot (the secure default), which means re-pairing the extension on each restart. With it, the token is stored 0600 at ~/.chrome-mcp/token and reused; the extension's keepalive auto-reconnects with no manual step. CHROME_MCP_TOKEN pins the token explicitly (and is never written to disk).

2. Load the extension — required; the server can drive nothing without it.

Two ways to get it:

• Install from the Chrome Web Store — one click, no Developer mode, and Chrome keeps it updated. The Web Store build is reviewed before each release, so it can trail the npm package by a version; it pairs with any server and simply skips features it predates.
• Load the bundled folder (below) — always matches the npm package you just installed, and the right choice when you want the newest behaviour.

The extension ships prebuilt inside the npm package, and every time the server boots it copies it to a plain folder right under your home directory:

~/chrome-mcp-extension          (macOS / Linux)
%USERPROFILE%\chrome-mcp-extension   (Windows)

So after step 1 has started the server once (restart your client, or /mcp in Claude Code), the folder is already there. To create it without a client, or to print the exact path:

npx -y @mehmoodqureshi/chrome-mcp --extension-path

Then chrome://extensions → enable Developer mode → Load unpacked → pick chrome-mcp-extension in your home folder. After upgrading the package the server refreshes the files on its next boot and the extension reloads itself within 30 seconds; nothing to click. CHROME_MCP_EXTENSION_DIR moves the folder somewhere else. (Working from a git clone instead? Run npm install && npm run build:ext first — extension-dist/ is gitignored, and the server mirrors it to the same home folder.)

3. Pair it — usually nothing to do. Every time the server boots it writes pairing.json (mode 0600, never shipped in the tarball) into the very chrome-mcp-extension folder you just loaded. The extension reads that file from its own folder on startup and pairs itself, so the toolbar badge turns green with no token to paste. Load the extension before the server has ever run? It re-checks every 30 seconds and pairs as soon as the file appears.

Where to see the badge: it sits on the extension's icon in Chrome's toolbar, not on the chrome://extensions page. Chrome hides new extensions behind the puzzle-piece button at the right of the address bar, so click that, find MCP Extension for Chrome, and click the pin next to it once; the icon then stays in the toolbar. Hover it for the status in words.

Manual fallback (a copied folder, a read-only home): run npx -y @mehmoodqureshi/chrome-mcp --print-pairing, open the extension's Options page, and paste the port + token from ~/.chrome-mcp/handshake.json. Values saved there take precedence over the bundled file.

Running more than one session

Every MCP host session (each Claude terminal, tab or window) starts its own chrome-mcp, and they all share your Chrome at once. The first one to start owns the bridge port and the extension connections — the hub. Each later session finds the port held by a live chrome-mcp and joins it as a peer: its tool calls are relayed through the hub to the same browsers, so every session keeps working side by side. Nobody is disconnected.

When the hub's session ends, its peers race for the port; one takes it over (with the same token, so the extension re-pairs by itself within a few seconds) and the rest join the new hub. A call that was in flight at that moment fails once with EXTENSION_DISCONNECTED and is retried automatically when it is safe to repeat.

Peers authenticate with the pairing token from the 0600 handshake file, so only your own OS user can join. A chrome-mcp too old to share the port is replaced as before: it is verified to be chrome-mcp, then stopped. Anything that isn't a verified chrome-mcp is never touched — a port held by some other program is reported, never killed.

Sessions share one browser, so they also share its tabs: two sessions driving the same tab at the same moment will step on each other. Give each session its own tabs (tab_new), or its own Chrome profile (below).

Each session can also drive several browsers at once: load the extension in each Chrome profile and they all pair to the same server, each under its own profile name. Tools act on the active profile — pick it with --profile <name> at startup or the profile_use tool at runtime.

Naming is automatic. Chrome won't tell an extension which profile it runs in, so each install keeps a random id and the server names it: the first browser is default, the next profile-2, then profile-3, and so on. Names are stored in ~/.chrome-mcp/profiles.json, so a browser keeps its name across restarts. chrome_status lists every paired browser (with its active tab as a hint), and profile_rename gives one a friendly name (profile-2 → work). To pin a name yourself instead, type it into the extension's Options → Profile; that always wins.

Without --port, each server binds an ephemeral port (no conflict ever), but the port changes every boot — so you'd re-pair the extension each time. Pin --port plus --persist-token for a pair-once setup.

Windows

WSL2 is not required — native Windows works. One config change is, though: on Windows npx is npx.cmd, a batch shim, and MCP hosts spawn the server without a shell, which cannot execute a .cmd. So "command": "npx" fails to start. Wrap it in cmd /c:

{
  "mcpServers": {
    "chrome-mcp": {
      "command": "cmd",
      "args": ["/c", "npx", "-y", "@mehmoodqureshi/chrome-mcp",
               "--allow-domain", "example.com", "--enable-mutations",
               "--persist-token"]
    }
  }
}

Or from Claude Code: claude mcp add chrome-mcp -- cmd /c npx -y @mehmoodqureshi/chrome-mcp --allow-domain example.com

Everything else is the same — load %USERPROFILE%\chrome-mcp-extension and pair as above.

The tools cover tabs, navigation, interaction (click/type/press/hover/ scroll/select_option), reads (get_text/get_html/screenshot/eval/wait_for), an accessibility snapshot (interactive elements with stable refs the model can target instead of guessing CSS selectors), session access (get_cookies/storage), helpers (extract_links/read_as_markdown/fill_form/download_file/upload_file), and chrome_status. upload_file sets local file(s) on a file <input> without the OS dialog (requires --enable-uploads).

click/type accept trusted: true for real OS-level input (works on React/Vue controlled inputs); interactions auto-wait for the target to appear.

Driving several tabs at once — batch

batch runs many tool calls in one request — parallel (default) or serial (with optional stopOnError). Each sub-op goes through the same policy gate, rate limit, and error handling as a direct call (no bypass, no nesting). Use it to fan work out across tabs:

// open three product pages (background, so they don't fight for focus)…
{ "name": "batch", "arguments": { "ops": [
  { "tool": "tab_new", "args": { "url": "https://a.example/p" } },
  { "tool": "tab_new", "args": { "url": "https://b.example/p" } },
  { "tool": "tab_new", "args": { "url": "https://c.example/p" } }
]}}

// …then read them all at once (wall-clock ≈ the slowest one, not the sum)
{ "name": "batch", "arguments": { "ops": [
  { "tool": "get_text", "args": { "tabId": "<a tabId>" } },
  { "tool": "get_text", "args": { "tabId": "<b tabId>" } },
  { "tool": "get_text", "args": { "tabId": "<c tabId>" } }
]}}

In parallel mode, tab-scoped ops must pass an explicit tabId — the active-tab default is unsafe under concurrency, so it's rejected rather than silently mis-routed. (tab_new, tabs_list, chrome_status are exempt.)

tab_new focuses the new tab by default (so "open X" behaves like opening a link, instead of replacing your current page — use tab_new, not navigate, to open without losing the current tab). Pass active: false to open in the background; parallel batches do this automatically.

Reaching into iframes and shadow roots

A selector that "should" match but doesn't almost always means the element is somewhere your selector cannot reach: inside an <iframe> (checkout widgets, OAuth consent screens, embedded editors) or inside a web component's shadow root.

Shadow roots are handled for you — every selector and every ref now resolves through open shadow roots, so anything snapshot shows you is something you can click. (It used to show you elements no click could reach: the snapshot walked shadow roots, the actions did not.)

Frames are opt-in, because reaching into one is a decision:

frames_list {}                                  // what frames exist, and their URLs
click { "selector": "#pay", "allFrames": true } // find it in whichever frame has it
get_text { "frameId": 7 }                       // pin one frame

Every frame is authorized against its own URL before anything runs in it, so an allowlisted page embedding a third-party iframe does not become a way to read that third party. Frames whose origin isn't on your allowlist are skipped.

Seeing why a page broke — console_logs, network_log, dialogs

Reading the DOM tells you what a page looks like after it failed, not why. With --enable-observers, an in-page hook records console output, uncaught errors, and fetch/XMLHttpRequest traffic, and intercepts native dialogs:

console_logs { "level": "error" }        // the exception the page swallowed
network_log  { "failedOnly": true }      // the 500 behind the blank screen
dialogs      { "policy": "accept" }      // answer confirm() with true from here on

It is off by default and deliberately so: the hook patches console, fetch, XMLHttpRequest and the dialog functions on every allowlisted page in your real browser. When it's on, it is registered only for the domains on your allowlist, at document_start (so it catches load-time failures), and nothing it records leaves the page until a tool call reads it — through the same gate as any other page read.

Dialog interception is also a fix, not just an observation: alert/confirm/ beforeunload block the renderer, so a click that opened one used to hang every injected script until the command timed out and reported TIMEOUT with nothing to point at. With observers on, the dialog is answered (dismiss by default: confirm → false, prompt → null) and recorded.

What network_log sees: the requests page code makes — fetch and XMLHttpRequest, with method, URL, status and duration — plus Resource Timing entries (scripts, images, styles) when you ask for them. Not the document request, redirects, or headers. That is the cost of not holding a debugger session open on your browser.

Only what changed — snapshot { diff: true }

A snapshot is the most expensive read in the tool surface, and the loop that uses it most (snapshot → click → snapshot) re-sends a page that is mostly identical every time. Ask for the delta instead:

snapshot { "diff": true }                       // added / removed / changed only
click { "selector": "#save", "snapshotAfter": true }   // what the click changed

Nodes are matched across snapshots by role + accessible name, not by ref — refs renumber in document order on every snapshot, so diffing on them would report an unchanged button as removed-and-re-added the moment anything above it appears.

Targeting by role and name

Actions accept a locator instead of a CSS selector, so you don't need a snapshot first just to learn a ref:

click { "role": "button", "name": "Sign in" }
type  { "role": "textbox", "name": "Email", "text": "a@b.com" }

Resolution is server-side and refuses to guess: an ambiguous locator fails with the candidates listed rather than acting on the first one (pass nth to pick).

Did the session expire? — auth_check and failOnAuthWall

Reusing a signed-in Chrome removes the login step, but a session cookie can still expire mid-run. Without a distinct signal the next step fails as SELECTOR_NOT_FOUND or TIMEOUT, and an eval harness scores the run as an agent failure when it was an auth failure. Every snapshot now carries an authWall verdict when the page looks like a sign-in wall, and there is a dedicated probe:

auth_check {}                                   // { authRequired, confidence, signals }
auth_check { "failOnAuthWall": true }           // [AUTH_REQUIRED] error instead
navigate  { "url": "https://app.example.com/dashboard", "failOnAuthWall": true }
snapshot  { "failOnAuthWall": true }

For a harness, set it once instead of per call:

npx -y @mehmoodqureshi/chrome-mcp --allow-domain app.example.com --enable-mutations --fail-on-auth-wall

With the flag on, every step that can move the tab (navigate, click, type, select_option, press, fill_form, back, forward, reload) checks the page it landed on and fails with [AUTH_REQUIRED] if that page is a sign-in wall, and a wait_for that times out on such a page reports [AUTH_REQUIRED] instead of [TIMEOUT]. Each guarded step costs one extra snapshot round-trip; with the flag off the cost is zero. [AUTH_REQUIRED] is where a harness pauses for a human to sign in again in the same Chrome, then retries the step. chrome-mcp never re-authenticates on its own: it holds no credentials, by design.

Detection reads only what the snapshot already has: the URL (sign-in routes, identity-provider hosts such as accounts.google.com, login.microsoftonline.com, Okta, Auth0), the title, password fields, and sign-in controls. high confidence needs two independent cues (a password field plus a sign-in button, say); a lone password field or a bare /auth/... URL is medium. A header "Sign in" link on an ordinary page never counts. failOnAuthWall fires only on high, so a harness can bucket [AUTH_REQUIRED] separately from every other failure while a settings page with a "current password" field carries on.

Printing — print_pdf

print_pdf { "landscape": true }

Renders through Chrome's own print pipeline and saves to the task's results/ dir, returning the path and size. The bytes themselves are never returned — a PDF is megabytes of base64 no model can read.

Paying less per turn — --tools

Every MCP server you connect costs context before you ask it anything: the host sends the whole tool catalog to the model on every turn. chrome-mcp's 39 tools are 27 KB of JSON Schema, about 6.9k tokens, on each one.

Most runs need a handful of them. --tools advertises only those:

npx -y @mehmoodqureshi/chrome-mcp \
  --allow-domain app.example.com --enable-mutations \
  --tools tabs_list,tab_new,navigate,snapshot,click,type,get_text

That surface is 6.0 KB, ~1.5k tokens — an 82% cut against the full catalog, for a run that was never going to print a PDF or upload a file.

• Comma-separated and repeatable: --tools navigate,get_text --tools click.
• A tool left out is hidden from tools/list and refused if called — a batch op naming it fails the same way an unknown tool does. Hiding a tool is a real restriction, not a display filter. It is not a substitute for the policy gate, though: --tools eval still does nothing without --unsafe-enable-eval.
• An unknown name fails at startup and prints the catalog, so a typo can never quietly drop click from the surface.
• chrome-mcp --help prints the full catalog of 39 names to pick from.

Status

v0.5.0 — safe multi-tab concurrency. Adds the batch fan-out tool, makes parallel tab automation race-free (explicit-tabId guard; per-tab chrome.debugger serialization; collision-free tab_new), captures screenshots via chrome.debugger (a specific tab without stealing focus — plus true full-page and element capture), and focuses newly opened tabs by default. 111 automated tests + a gated headed extension smoke.

v0.2.0 — all six build phases complete and green. End-to-end working: npx chrome-mcp ⇄ bridge ⇄ extension ⇄ your real Chrome, with a Playwright CDP fallback. v0.2 adds the accessibility snapshot + element refs, auto-wait, cookies/storage/select_option, trusted input (chrome.debugger), a toolbar status badge, and a stable pairing token (--persist-token).

• Phase 0 — Contracts & skeleton: shared/protocol.ts (wire contract), src/executor/types.ts (Executor interface), src/security/policy.ts (default-deny policy + capability gates), src/config.ts (CLI/env/policy resolution), build + test harness.
• Phase 1 — MCP server + StubExecutor: mcp/server.ts (clean-stdout stdio), mcp/tools.ts (28-tool catalog + never-throw dispatch + drift-check), validators/envelopes/helpers, ExecutorManager + StubExecutor, cli.ts. Point an MCP host at node dist/src/cli.js today.
• Phase 2 — WebSocket bridge + auth: bridge/server.ts (loopback WS, hello-token gate, welcome/unauthorized, displacement), bridge/auth.ts (per-boot 256-bit token, atomic-0600 handshake, SHA-256 timingSafeEqual), bridge/connection.ts (id-correlation, method-aware timeouts, backpressure, reject-all-on-close, heartbeat).
• Phase 3 — ExtensionExecutor + CdpExecutor + selection: executor/extension-executor.ts (Executor over the bridge), executor/cdp-executor.ts (Playwright connect/launch + lock recovery + tab resolution), executor/select.ts (extension-if-ping-responsive else CDP). CLI now starts the bridge, writes the 0600 handshake, and serves a real backend. Adds playwright.
• Phase 4 — MV3 extension: extension/ — manifest.json, sw/ws-client.ts (dial + hello/welcome + pong), sw/executor.ts (chrome.scripting/chrome.tabs command impls), sw/router.ts (never-throw + drift), sw/background.ts (top-level listeners + 25s keepalive/reconnect), options page (manual pairing), esbuild build → extension-dist/. Verified by a live --load-extension smoke (pair → navigate → get_text). Adds esbuild + @types/chrome.
• Phase 5 — Helpers, downloads, HITL: hardened download_file (shared/download.ts — path-traversal/dangerous-ext sanitize + size cap, wired into both backends), richer read_as_markdown, and a human-in-the-loop harness (hitl/ — npm run test:hitl [-- --include-mutating]) with pure, unit-tested gating. 50 automated tests.
• Phase 6 — Packaging & docs: files whitelist (ships dist/src, dist/shared, extension-dist, LICENSE, blueprint — not source/tests), prepack build, bin, quickstart + .mcp.json snippet. Verified by a tarball install smoke (npm pack → install → MCP tools/list).

Security posture (default)

Deny-all safe mode. With no policy configured: empty domain allowlist, eval off, downloads off, mutating tools off. Opt in explicitly:

chrome-mcp --allow-domain example.com --enable-mutations
chrome-mcp --policy ./policy.json          # see policy.example.json
chrome-mcp --unsafe-all-domains            # loud footgun
chrome-mcp --enable-observers              # console/network/dialog capture (patches page globals)
chrome-mcp --redact                        # scrub secret-shaped strings out of page reads

What comes back is gated too. The allowlist decides which pages may be read; it says nothing about what is on them. A logged-in page routinely renders a session token into a script tag or an API key onto a settings screen.

• Password field values are always suppressed — in get_html, and in snapshot, where the field still appears (so you can type into it) flagged secret: true with no value. No flag, no opt-in: nobody wants those characters.
• --redact additionally scrubs secret-shaped strings — JWTs, AWS/GitHub/Slack/ Google keys, Bearer headers, private-key blocks — out of get_text, get_html, read_as_markdown and eval. It is opt-in because a pattern will eventually fire on something you actually wanted. --redact-pattern <regex> adds your own (and implies --redact); an invalid one fails at startup rather than silently never matching.
• Redaction runs before the output cap, so a truncated read cannot leak what a full one would have hidden.

Every call is recorded to the task's history.jsonl with the URL it touched, the policy verdict (allowed/denied), how long it took, how many bytes came back, and how many secrets were scrubbed — so "what did the agent do in my browser" has an answer after the fact.

The per-boot 256-bit token in ~/.chrome-mcp/handshake.json (mode 0600) is the only trust boundary; it is never written to stdout/stderr. On POSIX the mode is re-verified after every write and the server fails closed if the file ends up group/other-accessible. Windows has no such bits — chmod there only toggles the read-only attribute — so the check is skipped and the token's confidentiality rests on the per-user ACL of %USERPROFILE%\.chrome-mcp.

Telemetry

The chrome-mcp server sends anonymous usage statistics to PostHog, so the project can see how many installs are active, which versions and platforms are in use, and which tools fail most. A notice is printed the first time it runs.

What is sent: a random install id (kept in ~/.chrome-mcp/telemetry.json), the chrome-mcp version, OS, CPU architecture and Node major version, whether the session owns the bridge port or shares it, how many browsers are paired, and per-tool call and error counts with error codes — batched every 10 minutes.

What is never sent: URLs, domains, tool arguments, page content, screenshots, cookies, profile names, tokens, file paths, or anything you type. Events are personless and GeoIP lookup is disabled.

The browser extension sends nothing — it only ever talks to 127.0.0.1.

Turn it off with any of:

CHROME_MCP_TELEMETRY=0     # or false / off
DO_NOT_TRACK=1
--no-telemetry             # server flag

Develop

npm install
npm run typecheck       # server/test sources
npm run typecheck:ext   # extension sources (@types/chrome)
npm run build:ext       # bundle the extension → extension-dist/
npm test                # builds, then runs node --test on dist/test
RUN_EXT_SMOKE=1 node --test dist/test/extension-smoke.test.js   # live, headed

The extension

Published on the Chrome Web Store as MCP Extension for Chrome. Extension versions move only when extension/ changes, so the listed build can sit a release behind the npm package; the two negotiate capabilities on connect, so an older extension loses features rather than breaking.

extension/ builds (esbuild) to extension-dist/, loaded via chrome://extensions → Load unpacked → select ~/chrome-mcp-extension, the mirror the server refreshes from extension-dist/ on every boot (loading extension-dist/ directly also works). It pairs itself from the pairing.json the server writes into that folder; the Options page paste of port + token from ~/.chrome-mcp/handshake.json (run npx -y @mehmoodqureshi/chrome-mcp --print-pairing to get the path) is only the fallback.

Reads/interaction use chrome.scripting/chrome.tabs — no "is being debugged" banner, CSP-safe reads (isolated world), testable under Playwright. chrome.debugger is used only where it's needed and worth it: trusted: true input (real OS-level events on React/Vue inputs) and screenshot (captures a specific tab without activating it — safe under parallel batch — with true full-page and element capture). Those ops show the debug banner while attached; the session lingers 1.5s after the last op so a burst of them attaches once. Screenshots are JPEG (quality 70) at CSS-pixel size by default — pass format: "png", quality, or scale to change that.