claude-chrome
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claude-chromeNavigate to example.com and take a screenshot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
claude-chrome
Claude-in-Chrome on steroids: MV3 extension + local hub daemon + MCP server. Full plan in PLAN.md.
Build
npm install
npm run buildRelated MCP server: monkeysee
Install the extension
Open
chrome://extensions, enable Developer mode."Load unpacked" → select the
extension/folder.The toolbar badge shows
●(green) when connected to the hub.
Register the MCP server
Claude Code (CLI):
claude mcp add claude-chrome -- node /Users/edem/Personal/claude-chrome/daemon/dist/index.jsClaude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"claude-chrome": {
"command": "node",
"args": ["/Users/edem/Personal/claude-chrome/daemon/dist/index.js"]
}
}
}The MCP server auto-spawns the hub (ws://127.0.0.1:48333) if it isn't running.
Start it manually with npm run hub to watch logs.
Tools
Tool | What |
| Open URL in the active (or new) tab, wait for load |
| Semantic page outline with |
| Act on |
| Visual/layout/animation audit: still-moving elements, horizontal overflow, broken images, covered/off-screen/tiny targets, unsettled animations |
| Pick |
| Mouse-over, wheel scroll, key combos ("ctrl+a", "Escape"), settle wait |
| Plain page text (main content when detectable) |
| JPEG of the visible viewport |
| Evaluate JS in the page (awaits promises) |
| Per-tab ring buffers; |
| Tab management |
| Resize the window |
| Plain-text intent → matching saved flow → deterministic replay + smoke report |
| Snapshot the last N journaled actions as a named flow |
| Replay / enumerate saved flows |
| Inspect recent replayable actions before saving |
| Names of credentials available for login flows |
Flows persist in ~/.claude-chrome/flows.json.
Login flows (secrets)
Login pages don't break the run. Put credentials in ~/.claude-chrome/secrets.json
(chmod 600) — you own this file; the values never pass through the chat, the journal,
saved flows, or logs:
{ "crm_user": "you@example.com", "crm_password": "…" }Then a login step is browser_type secret="crm_password". The hub swaps the name for
the value only on the wire to the browser; flow_save records the name, so a saved
login flow re-resolves the current value on every replay. secrets_list shows the names.
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Automate cloud Chrome—navigate, click, type, screenshot, run code, record screen video
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
Automate any website: discover, run and create browser scripts that work behind logins.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables browser automation with Puppeteer, supporting navigation, form interactions, and connection to active Chrome instances for comprehensive web page interaction.81,832 npm483MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to drive a real, logged-in Chrome browser for web automation tasks like navigation, clicking, typing, and screenshotting.4 npm1MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots.-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots, with optional API key authentication.-