Chrome extension-based MCP server that exposes an existing Chrome browser profile to AI assistants for tab management, page content, screenshots, interaction, history, bookmarks, and network inspection.
This server controls the user's existing Chrome browser profile and can reuse logged-in sessions., Tools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts., Use a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them., Do not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval., The project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
Privacy notes
Open tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model., Screenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents., Browser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
Author
hangwin
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 3 privacy notes across 4 risk areas. Review closely: credentials & tokens, network access.
4 areas
SafetyCredentials & tokensThis server controls the user's existing Chrome browser profile and can reuse logged-in sessions.
SafetyNetwork accessTools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts.
SafetyLocal filesUse a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them.
SafetyGeneralDo not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval.
SafetyGeneralThe project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
PrivacyCredentials & tokensOpen tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model.
PrivacyCredentials & tokensScreenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents.
PrivacyGeneralBrowser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
Safety notes
This server controls the user's existing Chrome browser profile and can reuse logged-in sessions.
Tools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts.
Use a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them.
Do not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval.
The project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
Privacy notes
Open tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model.
Screenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents.
Browser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
Prerequisites
Node.js 20 or newer and npm or pnpm.
Chrome or Chromium browser.
Latest Chrome MCP extension release from the project repository.
Globally installed mcp-chrome-bridge package.
MCP client that supports streamable HTTP, or the documented stdio fallback.
Chrome MCP Server is an extension-based MCP server for controlling and
inspecting a local Chrome browser. Unlike browser automation servers that launch
a separate clean browser, this project is designed to work with an existing
Chrome profile, including open tabs, settings, extensions, and login state.
It uses a Chrome extension plus the mcp-chrome-bridge package. The project
documents a streamable HTTP setup generated by the extension and an alternate
stdio bridge path for clients that do not support streamable HTTP.
These sources were reviewed on 2026-06-05. Prefer the live repository for
current release downloads, bridge installation steps, supported transports, and
tool lists.
Features
Streamable HTTP MCP endpoint through a local Chrome extension bridge.
Stdio fallback documented for MCP clients that do not support streamable HTTP.
Access to existing Chrome tabs and logged-in browser state.
Browser window and tab listing, switching, navigation, and close operations.
Screenshots, page content extraction, semantic tab content search, console
output, and interactive element discovery.
Network capture and custom request tooling.
Click, form fill/select, keyboard, history, and bookmark tools.
Installation
Install the bridge:
npm install -g mcp-chrome-bridge
Then download and load the latest Chrome extension release from the project
repository, connect it, and use the MCP configuration generated by the
extension. If a client only supports stdio, use the fallback path documented in
the project README and point the client at the installed stdio bridge file.
Capture screenshots and page content for UI debugging.
Inspect network requests while reproducing a web application issue.
Automate browser actions in a dedicated test profile.
Search browser tab content semantically across active work.
Safety and Privacy
This server is powerful because it works with the user's real Chrome session.
Prefer a separate Chrome profile for agent work, keep sensitive accounts closed,
and require human confirmation before actions that submit forms, change account
state, purchase goods, send messages, or alter data.
Treat screenshots, tab content, browsing history, bookmarks, and network
captures as sensitive. They may contain private application data or personal
information.
Duplicate Check
content/mcp/chrome-devtools-mcp-server.mdx covers the official Chrome
DevTools MCP server. This entry covers the separate hangwin/mcp-chrome
extension-based server that uses an existing Chrome profile.
Show that Chrome MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/chrome-mcp-server)
How it compares
Chrome MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
2 trust signals differ across this comparison (Source provenance, Submitter).
Chrome extension-based MCP server that exposes an existing Chrome browser profile to AI assistants for tab management, page content, screenshots, interaction, history, bookmarks, and network inspection.
Browser-control MCP server and CLI that lets AI agents use a real Chrome session, including logged-in browser state, site adapters, DOM snapshots, authenticated fetches, network traces, screenshots, and page actions.
Bowmark hosted MCP server serving pre-computed website navigation recipes for reliable browser automation from Claude, with optional Bearer API key auth.
✓This server controls the user's existing Chrome browser profile and can reuse logged-in sessions.
Tools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts.
Use a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them.
Do not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval.
The project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
✓BrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab.
Because it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent.
Require human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms.
Use a test profile or non-production account for end-to-end testing and repetitive automation.
✓bb-browser can control a real browser session, inspect pages, click elements, fill inputs, evaluate JavaScript, fetch URLs with browser authentication, capture screenshots, and inspect network traffic.
Commands may act as the logged-in user on social, finance, job, developer, shopping, and knowledge websites.
Keep the daemon bound to trusted local interfaces unless you deliberately configure remote access through a private network.
Review community site adapters before using them with authenticated accounts or valuable sessions.
Require human approval before posting, submitting forms, changing account settings, applying to jobs, making purchases, or running destructive site actions.
✓Navigation recipes may include steps that submit forms or trigger purchases if misused in automation.
Site layouts change; recipes can become stale and cause failed or unintended UI actions.
Bearer API keys should be stored in connector headers, not embedded in prompts or repositories.
Automating authenticated sessions may violate target site terms; obtain permission first.
Privacy notes
✓Open tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model.
Screenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents.
Browser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
✓Connected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model.
Logged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents.
Although the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
✓Tab URLs, titles, DOM snapshots, page content, selected elements, screenshots, network requests, responses, console output, traces, and authenticated fetch results may be exposed to the MCP client and model.
Browser login state is used by the page and browser; even if cookies are not extracted directly, commands can act through authenticated sessions.
Network request bodies and response data may contain tokens, account data, personal messages, search history, customer information, or internal application data.
The upstream privacy doc says communication is local and there is no telemetry or external server, but model providers still receive any data your MCP client sends in prompts or tool results.
✓Site names and flow intents you request may be logged by Bowmark for recipe matching.
Recipes can describe login or checkout paths; do not share full recipe dumps containing session hints publicly.
Optional API keys tie usage to your Bowmark account and billing profile.
Prerequisites
Node.js 20 or newer and npm or pnpm.
Chrome or Chromium browser.
Latest Chrome MCP extension release from the project repository.
Globally installed mcp-chrome-bridge package.
Node.js installed for the MCP server.
Chrome or compatible Chromium browser.
BrowserMCP extension installed from the project site.
MCP client such as Claude, Cursor, VS Code, Windsurf, or another compatible host.
Node.js 18 or newer.
Chrome session, local daemon, and Chrome extension or supported OpenClaw browser path configured according to the upstream README.
MCP client such as Claude Code, Codex, Cursor, or another compatible host.
Explicit approval to let an agent use the active browser's logged-in state.
Claude Pro, Team, or Enterprise with Connectors support, or Claude Code with HTTP MCP transport.
Optional Bowmark API key for authenticated tiers and extended recipe catalog access.
Browser or automation client that can consume Bowmark navigation recipes if executing flows end-to-end.
Compliance review before automating logins or transactions on third-party sites.
Install
npm install -g mcp-chrome-bridge
npx @browsermcp/mcp@latest
npx -y bb-browser --mcp
claude mcp add --transport http bowmark https://api.bowmark.ai/mcp