Agent skill

AIPex Browser Control

by AIPexStudio in AIPexStudio/AIPex

Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads.

MITAuto-check passedProductivity & Automation

Install AIPex Browser Control

skills CLI
$ npx skills add AIPexStudio/AIPex --skill aipex-browser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AIPexStudio/AIPex aipex-browser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AIPexStudio/AIPex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill .claude/skills/aipex-browser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aipex-browser
GitHub stars
1.3k
Token cost
~1.8k tokens
SKILL.md length
610 words
Files
2 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads.

  • Works in 2 steps: Register the MCP Server → Connect the AIPex Extension to the Bridge
  • Automating a multi-step workflow in Chrome
  • SKILL.md covers When to Use This Skill, Prerequisites, Step 1: Register the MCP Server and Step 2: Connect the AIPex…, plus 4 more sections
  • Calls claude

What it does

AIPex is a Chrome extension that exposes 30+ browser automation tools over the Model Context Protocol. The agent, as an MCP client, talks over stdio to aipex-mcp-bridge, which connects by WebSocket to the extension and on to the browser APIs, so Chrome tabs can be controlled in natural language: clicking, typing, navigating, capturing screenshots and downloading content.

Setup has two steps. First register the MCP server, with npx running aipex-mcp-bridge automatically, using the config shown for Cursor, Claude Desktop, Claude Code, VS Code Copilot or Windsurf. Then open the extension options in Chrome, enter ws://localhost:9223 in the WebSocket Connection section and connect, or use a custom port instead. It suits multi-step workflows, data extraction, tab management across windows and browser-assisted accessibility, UX and regression testing, and a tools reference file lists the available tools.

When your agent uses it

  • Automating a multi-step workflow in Chrome
  • Filling forms or clicking through a web page
  • Capturing screenshots of browser tabs
  • Managing tabs across browser windows

Example prompts

  • “Open the pricing page in Chrome and take a screenshot.”
  • “Fill in the signup form on this page with test data and submit it.”
  • “List all my open tabs and close the ones about the old dashboard.”

Requirements

  • The AIPex Chrome extension installed
  • Node.js 18 or newer
  • The aipex-mcp-bridge MCP server registered, run through npx

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Register the MCP Server
  2. Connect the AIPex Extension to the Bridge

What it can do on your machine

Read from SKILL.md and the folder at commit 4173fa8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AIPex Browser Control loads about 1.8k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 610 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AIPexStudio/AIPex at commit 4173fa8, republished under its MIT licence (© AIPexStudio). 610 words, ~1,793 tokens.

Download SKILL.mdSave it as .claude/skills/aipex-browser/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
aipex-browser
description
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
version
1.0.0

AIPex Browser Control

AIPex is a Chrome extension that exposes 30+ browser automation tools over the Model Context Protocol (MCP). Once connected, the agent can control any Chrome tab using natural language — clicking, typing, navigating, capturing screenshots, downloading content, and more.

Architecture:

Agent (MCP client) ──stdio──▶ aipex-mcp-bridge ──WebSocket──▶ AIPex Chrome Extension ──▶ Browser APIs

When to Use This Skill

Use this skill when the user wants to:

  • Navigate to URLs, click links, fill forms, or interact with any web page
  • Automate multi-step browser workflows
  • Extract or download data from web pages
  • Capture screenshots of browser tabs
  • Manage multiple tabs across browser windows
  • Perform browser-assisted testing (accessibility, UX, regression)

Prerequisites

  • AIPex Chrome extension installed (available on the Chrome Web Store or via developer build)
  • Node.js >= 18 installed on the local machine

The user is assumed to have AIPex installed. The agent only needs to complete the two connection steps below.


Step 1: Register the MCP Server

Add the following to the agent's MCP configuration. No manual installation is needed — npx downloads and runs aipex-mcp-bridge automatically.

Cursor (.cursor/mcp.json)
json
{
  "mcpServers": {
    "aipex-browser": {
      "command": "npx",
      "args": ["-y", "aipex-mcp-bridge"]
    }
  }
}
Claude Desktop (claude_desktop_config.json)
json
{
  "mcpServers": {
    "aipex-browser": {
      "command": "npx",
      "args": ["-y", "aipex-mcp-bridge"]
    }
  }
}
Claude Code (CLI)
bash
claude mcp add aipex-browser -- npx -y aipex-mcp-bridge
VS Code Copilot (.vscode/mcp.json)
json
{
  "servers": {
    "aipex-browser": {
      "command": "npx",
      "args": ["-y", "aipex-mcp-bridge"]
    }
  }
}
Windsurf (mcp_config.json)
json
{
  "mcpServers": {
    "aipex-browser": {
      "command": "npx",
      "args": ["-y", "aipex-mcp-bridge"]
    }
  }
}
Custom port (optional)

The bridge listens on localhost:9223 by default. To use a different port:

json
{
  "mcpServers": {
    "aipex-browser": {
      "command": "npx",
      "args": ["-y", "aipex-mcp-bridge", "--port", "9224"]
    }
  }
}

Then use ws://localhost:9224 in Step 2.


Step 2: Connect the AIPex Extension to the Bridge

After the MCP server is registered and running:

  1. Open Chrome and click the AIPex extension icon
  2. Go to Options (or right-click the icon → "Extension options")
  3. Find the WebSocket Connection section
  4. Enter: ws://localhost:9223
  5. Click Connect

The bridge and extension will handshake, and all browser tools will become available to the agent.

Verifying the connection: If only a single tool called check_aipex_connection is visible, the extension has not yet connected. Follow Step 2 again, then reload the MCP server in agent settings.


Tool Usage Strategy (IMPORTANT)

Always follow this priority order to minimize token cost and latency:

Priority 1 — search_elements (always try first)

Query the page's accessibility tree to find elements and get their UIDs. Fast, cheap, requires no screenshot.

search_elements(tabId, "{button,input,textarea,select,a}*")
Priority 2 — UID-based interaction (preferred)

Use UIDs returned by search_elements to interact directly:

  • click(tabId, uid) — click any element
  • fill_element_by_uid(tabId, uid, value) — type into inputs
  • hover_element_by_uid(tabId, uid) — reveal menus or tooltips
Show full SKILL.md (251 more words)Show less
Priority 3 — capture_screenshot + computer (high-cost fallback only)

Use only when search_elements fails after two different query attempts, or when pixel-level interaction is required (canvas, drag-and-drop, sliders).

  1. capture_screenshot(sendToLLM=true) — see the page
  2. computer(action, coordinate) — click/type at pixel coordinates
Standard Workflow
get_all_tabs()
  → search_elements(tabId, "<pattern>")
  → click(tabId, uid)  OR  fill_element_by_uid(tabId, uid, value)
  → [capture_screenshot(sendToLLM=true) to verify if needed]

Available Tool Categories

CategoryToolsDescription
Tab Management8 toolsOpen, close, switch, pin, group tabs
UI Interaction7 toolsClick, fill, hover, keyboard, coordinate-based
Page Content4 toolsMetadata, scroll, highlight elements/text
Screenshots2 toolsCapture visible tab or specific tab
Downloads3 toolsSave text as markdown, download images
Human Intervention4 toolsRequest user input mid-automation

Key tools by category:

CategoryKey Tools
Tabget_all_tabs, switch_to_tab, create_new_tab, close_tab
UIsearch_elements, click, fill_element_by_uid, computer
Pageget_page_metadata, scroll_to_element, highlight_element
Screenshotcapture_screenshot, capture_tab_screenshot
Downloaddownload_text_as_markdown, download_image
Interventionrequest_intervention, list_interventions

To load complete parameter schemas and examples for every tool:

read_skill_reference("aipex-browser", "references/tools-reference.md")

Common Patterns

Navigate to a URL and click a button
create_new_tab("https://example.com")
→ search_elements(tabId, "*[Ss]ubmit*")
→ click(tabId, uid)
Fill a login form
get_all_tabs()
→ search_elements(tabId, "{input,textbox}*")
→ fill_element_by_uid(tabId, emailUid, "user@example.com")
→ fill_element_by_uid(tabId, passwordUid, "secret")
→ search_elements(tabId, "*[Ll]ogin*")
→ click(tabId, uid)
Extract page content to markdown
get_page_metadata()
→ download_text_as_markdown(content, "page-extract")
Visual verification
capture_screenshot(sendToLLM=true)

Troubleshooting

SymptomLikely CauseFix
Only check_aipex_connection visibleExtension not connected to bridgeOpen AIPex Options → set WebSocket URL → Connect
Port 9223 already in usePort conflict on machineUse --port 9224 in MCP config and ws://localhost:9224 in extension
search_elements returns 0 resultsPage uses canvas or non-semantic HTMLFall back to capture_screenshot(sendToLLM=true) + computer tool
Connection drops frequentlyService worker sleep cycleAIPex uses keepalive pings; reconnect extension from Options if needed
Tools appear but calls time outBridge not receiving WebSocket messagesRestart bridge: reload MCP server in agent settings

© AIPexStudio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skill of AIPexStudio/AIPex.

  • SKILL.md
  • references/tools-reference.md

Open the folder on GitHubat commit 4173fa8

Compare with similar skills

AIPex Browser Control next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AIPex Browser Control compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AIPex Browser Control this skillAIPexStudio/AIPex1.3k—~1.8kAutomated safety check: PassMIT
Competitor Monitorhanzili/hanzi-browse177—~2.8kAutomated safety check: PassCustom licence
Job Applierhanzili/hanzi-browse177—~2.4kAutomated safety check: PassCustom licence
Linkedin Prospectorhanzili/hanzi-browse177—~1.5kAutomated safety check: PassCustom licence
Open Supermarketsabracadabra50/open-supermarkets1171 repos~1.4kAutomated safety check: PassMIT
Claude in Chrome MCP Troubleshootingtrailofbits/skills7.4k4 repos~2.6kAutomated safety check: PassCC-BY-SA-4.0

Similar skills

  • Competitor Monitor

    hanzili/hanzi-browse

    Monitor competitor websites for changes. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~2.8k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed
  • Job Applier

    hanzili/hanzi-browse

    Apply to jobs from your real browser. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~2.4k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed
  • Linkedin Prospector

    hanzili/hanzi-browse

    Find people on LinkedIn and send personalized connection requests.

    177 GitHub stars~1.5k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed
  • Open Supermarkets

    abracadabra50/open-supermarkets

    Searches, compares and fills baskets across supermarkets in several countries, with delivery slots, checkout and nutrition data, as a CLI, MCP server or skill.

    117 GitHub starsUsed in 1 repo~1.4k tokens
    Productivity & AutomationAuto-check passed
  • Official

    Diagnoses why the Claude in Chrome MCP tools report the browser extension as not connected, with macOS-specific checks and a fix for the Claude.app native host conflict.

    7.4k GitHub starsUsed in 4 repos~2.6k tokens
    Agent WorkflowsAuto-check passed
  • X Marketer

    hanzili/hanzi-browse

    Professional X/Twitter growth skill. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~5.3k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed

More from AIPexStudio/AIPex

  • UX Audit Walkthrough

    AIPexStudio/AIPex

    Walks a Figma prototype or live webpage screen by screen and scores it against four minimalist usability principles.

    1.3k GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Audits a live webpage against eight core WCAG 2.2 success criteria, combining accessibility-tree inspection, visual screenshots and keyboard navigation tests, with evidence in the report.

    1.3k GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed

Questions about AIPex Browser Control

What does AIPex Browser Control do?

Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads. AIPex is a Chrome extension that exposes 30+ browser automation tools over the Model Context Protocol. The agent, as an MCP client, talks over stdio to aipex-mcp-bridge, which connects by WebSocket to the extension and on to the browser APIs, so Chrome tabs can be controlled in natural language: clicking, typing, navigating, capturing screenshots and downloading content.

When should I use AIPex Browser Control?

AIPex Browser Control fits situations like: automating a multi-step workflow in Chrome; filling forms or clicking through a web page; capturing screenshots of browser tabs; managing tabs across browser windows.

How do I install AIPex Browser Control in Claude Code?

Run `npx skills add AIPexStudio/AIPex --skill aipex-browser -a claude-code`. Or copy the skill folder (skill in AIPexStudio/AIPex) into .claude/skills/aipex-browser in your project. Claude Code loads it when a task matches its description.

How do I install AIPex Browser Control in Codex?

Run `npx skills add AIPexStudio/AIPex --skill aipex-browser -a codex`. Or copy the skill folder (skill in AIPexStudio/AIPex) into .agents/skills/aipex-browser in your project. Codex loads it when a task matches its description.

Can I use AIPex Browser Control in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AIPexStudio/AIPex --skill aipex-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aipex-browser, .gemini/skills/aipex-browser, .github/skills/aipex-browser and .opencode/skills/aipex-browser in your project.

What does AIPex Browser Control need to run?

Going by SKILL.md and its folder, AIPex Browser Control needs the command-line tools its instructions call (claude). Our summary lists: The AIPex Chrome extension installed; Node.js 18 or newer; The aipex-mcp-bridge MCP server registered, run through npx.

Does AIPex Browser Control access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AIPex Browser Control safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AIPex Browser Control use?

AIPex Browser Control is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AIPex Browser Control use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.2k tokens, read only when the agent opens those files.

What are the alternatives to AIPex Browser Control?

Skills that share tags, products or a category with AIPex Browser Control: Competitor Monitor (hanzili/hanzi-browse, 177 stars), Job Applier (hanzili/hanzi-browse, 177 stars), Linkedin Prospector (hanzili/hanzi-browse, 177 stars) and Open Supermarkets (abracadabra50/open-supermarkets, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AIPex Browser Control?

AIPexStudio (a GitHub organization) maintains it in AIPexStudio/AIPex, which has 1,260 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 26, 2026.

Source: AIPexStudio/AIPex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.