Skip to main content
Glama

BrowserMCP Extended · MCP Server

CI License: Apache 2.0 Node.js

39 MCP tools for automating your existing browser and inspecting HTTP/WebSocket traffic through a local Chrome extension.

BrowserMCP Extended connects an MCP-compatible AI client to the companion Chrome extension. It runs locally over stdio, exchanges correlated commands through a loopback WebSocket, and exposes browser operations as discoverable MCP tools. Existing browser sessions are reused; no separate cloud browser or project API key is required.

This is an independent modified distribution. See NOTICE for Browser MCP and Playwright MCP credits. Version 2.0.0 pairs with the 2.x extension.

Capabilities

Category

Tools

Examples

Navigation and references

11

Navigate, snapshot, click, type, select, drag, keyboard

Tabs

4

List, switch, open, close

DOM, frames, files

5

Read text/HTML, scroll, evaluate in a frame, assign a file input

Cookies and storage

4

Read cookies/storage; document.cookie-based write/delete

Screenshots

3

Viewport, full-page request, element location plus viewport image

Advanced interactions

4

CSS drag/drop, dialogs, clipboard, cache-bypassing reload

JavaScript and console

2

Evaluate expressions and read logs captured during evaluations

Network capture

6

Start, stop, list, detail, clear, HAR export

The authoritative tool reference documents all 39 unique tool names, parameters, required fields, and examples. Known limitations describes behavior that differs from a full browser testing or DevTools product.

Related MCP server: YaviControl MCP Server

Installation

Requirements: Node.js 22+, a recent desktop Chrome or Chromium, an MCP client with stdio support, and the companion extension installed in that browser.

git clone https://github.com/NEO10111/browsermcp-extended-mcp.git
cd browsermcp-extended-mcp
npm ci

There is no build step. This repository is installed from source; the README does not assume an npm registry release. The package is marked private to prevent accidental publication.

Clone and load the extension separately:

cd ..
git clone https://github.com/NEO10111/browsermcp-extended-extension.git

In chrome://extensions, enable Developer mode, click Load unpacked, and choose the extension directory. Open its popup and turn automation On.

Client configuration

Codex

Add this table to ~/.codex/config.toml and restart Codex:

[mcp_servers.browsermcp-extended]
command = "node"
args = ["/absolute/path/browsermcp-extended-mcp/server.js", "--execute-port", "9877"]

Use an absolute Node executable path if the client does not inherit your shell's PATH. Merge the entry into existing configuration rather than replacing it.

Other stdio MCP clients

Adapt the client-specific configuration location and use this server definition:

{
  "mcpServers": {
    "browsermcp-extended": {
      "command": "node",
      "args": ["/absolute/path/browsermcp-extended-mcp/server.js", "--execute-port", "9877"]
    }
  }
}

The MCP client launches the process and owns stdin/stdout. Running npm start in a terminal is useful for startup diagnostics, but it does not register tools with a client by itself. Logs go to stderr; stdout is reserved for MCP traffic.

Port and multiple clients

The default address is 127.0.0.1:9877. Set a different port with --execute-port N or the compatible --port N alias, then update the extension popup to match. The server does not kill a process occupying the port.

Multiple server processes can share one compatible local bridge. The first owns the browser socket; peers relay their requests through it. A remaining peer can retake the port if the owner exits. Sessions share browser state and per-tab captures; they are not isolated users or separate browser profiles.

First-use examples

Ask your MCP client to list tabs, select a tab, generate a snapshot, and click or type using references from that snapshot. Regenerate a snapshot after navigation or significant DOM changes.

A direct tool invocation uses the MCP name and arguments:

{"name":"browser_list_tabs","arguments":{}}
{"name":"browser_snapshot","arguments":{}}
{"name":"browser_type","arguments":{"element":"Search field","ref":"e1","text":"MCP","submit":false}}

e1 above is illustrative; use the actual reference returned by your page. JavaScript input is evaluated as an expression; wrap statements in an IIFE:

{"name":"execute_script","arguments":{"code":"(() => ({title: document.title, url: location.href}))()"}}

Network inspection

Capture must begin before the traffic you want to inspect:

{"name":"browser_network_start","arguments":{"tabId":123,"captureBodies":true}}

Reload the selected tab or trigger the action being inspected:

{"name":"browser_reload","arguments":{"hard":true}}

List and filter captured records:

{"name":"browser_network_list","arguments":{"tabId":123,"resourceType":"Fetch","status":200,"limit":50}}

Pass an exact returned id to inspect headers, POST data, response body, timing, errors, and WebSocket frames:

{"name":"browser_network_detail","arguments":{"tabId":123,"requestId":"12345.1:1"}}
{"name":"browser_network_export_har","arguments":{"tabId":123,"filePath":"/absolute/path/capture.har"}}
{"name":"browser_network_stop","arguments":{"tabId":123}}

tabId and requestId values are examples. browser_reload acts on the active tab, so select the captured tab before reloading. HAR files are written on the server machine; existing files are not overwritten. Without filePath, export returns HAR JSON. See network capture for limits and retention.

Development and verification

npm ci
npm run check
npm test
npm run docs:tools

The integration suite starts real stdio MCP processes and a simulated extension socket. It verifies tool discovery, command routing, port conflicts, concurrent clients, and ownership takeover. CI runs these checks on Node.js 22 and 24.

Run the real Chromium/extension test with both repositories checked out:

BROWSERMCP_EXTENSION_PATH=../browsermcp-extended-extension npm run test:browser

The test uses /usr/bin/chromium by default; override with CHROMIUM. It launches an isolated browser profile and local HTTP/WebSocket fixture, captures GET/POST, redirects, 404s and WebSocket frames, verifies screenshot coexistence and response content, then writes and reads a HAR file. No real account or internet site is needed for the fixture. The companion extension's unit suite runs in its own repo.

Architecture and safety

flowchart LR
  Clients[MCP clients] -->|stdio per process| Servers[Node.js MCP servers]
  Servers -->|shared loopback bridge| Extension[Chrome extension]
  Extension -->|Chrome APIs / CDP| Tabs[Browser tabs]

The browser profile is the user's real profile. The bridge has no authentication or Origin allowlist and must remain private to a trusted machine. Network records may contain credentials and sensitive response content. Data returned to the MCP client may be sent to that client's model provider. See SECURITY.md, architecture, and troubleshooting.

Contributing and license

See CONTRIBUTING.md, CHANGELOG.md, LICENSE, and THIRD_PARTY_NOTICES.md.

Available Tools

39 tools
browser_clickC

Perform click on a web page

Inputs: ref (required), element (required).

browser_clipboard_writeC

Write text to the browser clipboard

Inputs: text (required).

browser_close_tabC

Close a browser tab by its tab ID

Inputs: tabId (required).

browser_dialog_handleB

Handle a JavaScript dialog (alert, confirm, or prompt) by accepting or dismissing it

Inputs: action (required), promptText.

browser_dragB

Perform drag and drop between two elements

Inputs: endRef (required), startRef (required), endElement (required), startElement (required).

browser_drag_dropC

Perform a drag-and-drop operation between two elements identified by CSS selectors

Inputs: sourceSelector (required), targetSelector (required).

browser_execute_in_frameB

Execute JavaScript code inside a specific iframe

Inputs: code (required), frameId (required).

browser_get_console_logsB

Get the console logs from the browser

Inputs: no named parameters.

browser_get_cookiesC

Get all cookies for a specific URL

Inputs: url (required).

browser_get_htmlB

Get the HTML content of the page or a specific element

Inputs: selector, outerHTML.

browser_get_storageB

Read localStorage and/or sessionStorage of the active tab

Inputs: type.

browser_get_textC

Get the plain text content of the page or a specific element

Inputs: selector.

browser_go_backB

Go back to the previous page

Inputs: no named parameters.

browser_go_forwardB

Go forward to the next page

Inputs: no named parameters.

browser_hoverC

Hover over element on page

Inputs: ref (required), element (required).

browser_list_tabsA

List all open browser tabs with their IDs, URLs, and titles

Inputs: no named parameters.

browser_navigateC

Navigate to a URL

Inputs: url (required).

browser_network_clearA

Clear the captured network buffer without stopping an active capture.

Inputs: tabId.

browser_network_detailA

Read a captured request including headers, query URL, POST data, response body, timing, errors and WebSocket frames. Bodies can be unavailable or truncated; see bodyError and truncated fields.

Inputs: requestId (required), tabId.

browser_network_export_harA

Export captured traffic as HAR 1.2. Returns HAR JSON, or writes a new file on the MCP server machine if filePath is supplied. Existing files are not overwritten. Timing phases are aggregated; unavailable fields use HAR sentinel values.

Inputs: tabId, filePath.

browser_network_listA

List captured requests with IDs, URLs, methods, statuses, durations and failures. Supports filters and pagination. Use the returned id in browser_network_detail.

Inputs: url, limit, tabId, method, +3 more.

browser_network_startA

Start network capture on a tab. Captures future HTTP requests, responses, failures and WebSocket messages. Reload the page afterwards to capture initial loading. Starting an already active capture preserves it; starting a stopped capture resets its buffer.

Inputs: tabId, maxEntries, captureBodies.

browser_network_stopA

Stop capture and release the debugger. Recorded requests and captured bodies remain available until clear, restart or extension reload.

Inputs: tabId.

browser_new_tabB

Open a new browser tab, optionally navigating to a URL

Inputs: url.

browser_press_keyC

Press a key on the keyboard

Inputs: key (required).

browser_reloadA

Reload the current browser page, optionally with a hard refresh (cache bypass)

Inputs: hard.

browser_screenshotB

Take a screenshot of the current page

Inputs: no named parameters.

browser_screenshot_elementB

Take a screenshot of a specific DOM element identified by a CSS selector

Inputs: selector (required).

browser_screenshot_fullpageB

Capture a full-page screenshot (beyond the visible viewport)

Inputs: no named parameters.

browser_scrollC

Scroll the page or a specific element to given coordinates or into view

Inputs: x, y, behavior, selector.

browser_select_optionC

Select an option in a dropdown

Inputs: ref (required), values (required), element (required).

browser_snapshotA

Capture accessibility snapshot of the current page. Use this for getting references to elements to interact with.

Inputs: no named parameters.

browser_switch_tabC

Switch to a specific browser tab by its tab ID

Inputs: tabId (required).

browser_typeC

Type text into editable element

Inputs: ref (required), text (required), submit (required), element (required).

browser_upload_fileC

Upload a file to a file input element on the page

Inputs: filePath (required), selector (required).

browser_waitC

Wait for a specified time in seconds

Inputs: time (required).

execute_scriptC

Execute arbitrary JavaScript code in the active browser tab and return the result

Inputs: code (required), world, timeoutMs, captureConsole.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.9/5.0

    Scored across 39 tools

    Disambiguation3/5

    Most tools target a distinct resource+action, but browser_drag and browser_drag_drop appear to be near-duplicates with only a CSS-selector phrasing difference, forcing an arbitrary choice. Content-retrieval tools (browser_get_text, browser_get_html, browser_snapshot, browser_screenshot_element) also overlap somewhat, though descriptions provide workable guidance.

    Naming Consistency3/5

    The browser_ prefix is applied almost everywhere, but conventions mix: verb-first names (browser_click, browser_type, browser_get_text) sit alongside resource-then-verb names (browser_network_list, browser_network_detail, browser_screenshot_element). execute_script breaks the prefix entirely, and browser_drag vs browser_drag_drop is an inconsistent naming of essentially the same operation.

    Tool Count2/5

    At 39 tools the surface is heavy for a browser-automation server, and several clusters could be consolidated: three screenshot variants, six network-capture tools, and two drag implementations. Individually justifiable, but as a set it exceeds a comfortably scannable scope.

    Completeness4/5

    Coverage is broad: navigation, tabs, interaction, cookies, storage, console logs, dialogs, iframes, uploads, screenshots, and full network capture with HAR export. Minor gaps remain (no viewport/device emulation, no read-clipboard, no selector-based wait, no storage writes), but agents can work around them.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to control the Google Chrome browser through a Node.js WebSocket bridge and a dedicated browser extension. It provides tools for capturing screenshots, executing JavaScript, managing tabs, and extracting page content via the MCP protocol.
      2
      -
    • A
      license
      B
      quality
      B
      maintenance
      Turns Chrome into a local MCP server, giving AI agents 51 browser tools to inspect DOM, automate clicks, run JavaScript, audit security and accessibility, mock APIs, extract data, record demos, and more from any MCP client.
      92
      77 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables remote AI agents to control a local, authenticated desktop browser over MCP through an outbound WebSocket bridge and Chrome extension, supporting tab management, navigation, page reading, clicking, typing, scrolling, screenshots, and JavaScript evaluation.
      1
      MIT