local-browser
Drives an installed Google Chrome browser with a separate profile for safe web automation, including navigation, compact page snapshots, clicking, typing, scrolling, screenshots, and approval-gated form submissions.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
local-browser
A safe, token-lean local browser for AI agents: a CLI and MCP server that drives the Chrome or Edge already on your machine.
Status: v0.1, early. Works, but expect rough edges. Feedback welcome in Issues.
Why
Agents waste tokens on raw HTML, and handing them your everyday browser profile is risky. local-browser:
runs your installed Chrome/Edge with a separate profile, so no cookies or saved passwords from your normal browsing;
shows the agent compact text snapshots with numbered refs instead of HTML;
waits for a human "yes" in the browser before submitting forms or typing into password fields;
keeps to a domain policy (allow/block lists,
http(s)only, re-checked after redirects);logs every action to a local JSONL file, with typed text redacted.
Related MCP server: byob
Requirements
Node.js 22+
Google Chrome or Microsoft Edge
Windows or Linux, tested in CI. macOS should work but isn't tested in CI yet. No GPU needed.
Quick start
git clone https://github.com/janmm97/local-browser
cd local-browser
npm ci
npm run build
node dist/cli.js snapshot https://en.wikipedia.org/wiki/Web_browserUse it from Claude Code (or any MCP client)
claude mcp add local-browser -- node /path/to/local-browser/dist/cli.js mcpOther clients: run node /path/to/local-browser/dist/cli.js mcp as a stdio server. The browser window opens on the first tool call.
Usage
local-browser mcp [options] Run the MCP server on stdio
local-browser snapshot <url> [options] Print a compact snapshot of a page
--policy <file> Policy JSON
--browser <name> chrome (default) or msedge
--headless No window; steps that need approval are deniedThe profile and action log live in ~/.local-browser/ (profile/, actions.jsonl). Set LOCAL_BROWSER_HOME to move them.
MCP tools
Tool | What it does |
| Go to a URL (checked against the policy) |
| Compact page outline: |
| Click an element; submit buttons wait for approval |
| Fill a field; password fields and |
| Scroll the page |
| Go back |
| JPEG of the viewport (costs far more tokens than a snapshot) |
A snapshot looks like:
# Hacker News
url: https://news.ycombinator.com/
[2] link "Hacker News"
[3] link "new"
...Policy
Copy local-browser.policy.example.json and pass it with --policy:
{
"allowedDomains": ["wikipedia.org", "news.ycombinator.com"],
"blockedDomains": ["accounts.google.com"],
"confirm": ["submit", "password"],
"maxSnapshotChars": 12000
}allowedDomains: if not empty, only these domains and their subdomains can be visited.blockedDomains: never visited.confirm: steps that need a human click on Allow in a separate browser tab. Scripted clicks don't count. Remove a step from the list to let it run without asking.maxSnapshotChars: longer snapshots are cut (the agent can scroll).
Unknown keys are rejected, so a typo can't silently turn a rule off.
How many tokens does it save?
Measured on 2026-11-18 (Windows 11, Chrome), characters of raw HTML against a full, uncapped snapshot:
Page | HTML | Snapshot | Smaller by |
en.wikipedia.org/wiki/Web_browser | 413,306 | 31,397 | ~13× |
news.ycombinator.com | 34,365 | 10,553 | ~3× |
With the default maxSnapshotChars (12,000) the Wikipedia snapshot is cut to about 12 KB.
Known limits (v0.1)
The domain policy applies to page navigations, not to images, scripts or other subresources a page loads.
Redirects aren't checked while they happen: a redirected request (including a 307/308 re-POST of an approved form) is still sent; the agent is then taken off a blocked page.
Iframes aren't included in snapshots.
No downloads (they're turned off), uploads or tab-switching tool.
"Submit" approval: a click on a submit button (including
<button form=…>) or Enter viatypewaits for a human. The approval lets one form POST through, only to the target shown in the prompt; every other POST navigation is blocked, so page-JavaScriptform.submit()can't send data. Not covered:fetch/XHR requests, and forms that submit with GET. UseallowedDomainsfor sites you don't trust.Localhost and private network addresses (and the cloud metadata IP 169.254.169.254) are not blocked by default.
blockedDomainsmatches host names and exact addresses only (for examplelocalhost,127.0.0.1,[::1],169.254.169.254), not ranges like10.0.0.0/8; list the ones you need. Range blocking is planned for v0.2 (#7).Page text is untrusted: a page can hide instructions in invisible text that still appears in snapshots. The tool descriptions tell the model not to follow them, which is a hint, not a guarantee.
Password approval only fires for fields that are
type="password"when the agent types; a page can use a plain text field for a password.Approval needs a visible window; in
--headlessmode those steps are denied.The log stores URLs, which can contain query text a site puts there (for example search forms).
data-lb-refattributes are visible to page scripts. They are labels, not a security boundary.CI tests the approval prompt headless (including a hostile button label); the full headed flow is a manual check (
npm run build && node test/approval.manual.mjs).
Contributing
See CONTRIBUTING.md. Please follow our Code of Conduct.
Security
See SECURITY.md. Don't open public issues for vulnerabilities.
License
MIT, see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Let AI agents work in your own signed-in Chrome, with approvals and verified results.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to drive the Chrome, Brave, or Edge browser you are already logged into, working in a tab of its own with a visible cursor and real trusted input. You can pause, take over, or hand back control at any time, and consequential actions such as submitting, paying, sending, deleting, or uploading wait for your approval.1Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to drive the user's real, already-logged-in Chrome browser locally, so they can read and navigate pages, click, type, fill forms, take screenshots, and inspect cookies, tabs, console, and network traffic without headless browsers or remote-debugging ports.1 npmISC
- AlicenseNot gradedqualityBmaintenanceGives MCP-compatible AI agents a local, observable control plane for Edge, Chrome/Chromium, and Firefox, combining DOM/accessibility, screenshots, Windows UI Automation, and real mouse/keyboard input with verification, approvals, and audit logging.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to locally drive the user's own logged-in Chrome browser, including clicking, typing, reading pages, taking screenshots, running JavaScript, recording GIFs, and coordinating parallel agents across Chrome profiles and tab groups.21MIT