webpilot
Click on "Install 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., "@webpilotGo to https://news.ycombinator.com and extract the article titles"
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.
Webpilot
The web, through the eyes of a machine.
A semantic terminal browser that renders web pages as structured, numbered, interactive text. Built for LLM agents (via MCP), CLI-native developers, and automation pipelines.
Key insight: LLMs don't need to see a website — they need to understand it. Webpilot uses the accessibility tree (the same structure screen readers use) to represent any website as numbered elements that both humans and machines can interact with.
$ wpilot https://github.com
┌──────────────────────────────────────────────────────────────┐
GitHub: Let's build from here
https://github.com
└──────────────────────────────────────────────────────────────┘
[1] › link Sign in
[2] › link Sign up
[3] ⌕ searchbox Search GitHub
[4] # h1 Build and ship software on a single platform
[5] _ textbox Enter your email address
[6] ◆ button ⟦ Sign up for GitHub ⟧
~ › click 1
Navigated: github.com -> github.com/login
[1] # h1 Sign in to GitHub
[2] _ textbox Username or email address
[3] _ textbox Password
[4] ◆ button ⟦ Sign in ⟧
[5] › link Forgot password?
[6] › link Create an account
~ › type 2 octocat@github.com
~ › type 3 ••••••••
~ › ss github-login.png
Screenshot saved to github-login.pngThe screenshot webpilot saves:
Why Webpilot?
Browsh | Lynx | Carbonyl | Webpilot | |
JavaScript support | Yes | No | Yes | Yes |
SPAs (React, Next.js, Vue) | Yes | No | Yes | Yes |
LLM-parseable output | No | No | No | Yes |
MCP server for AI agents | No | No | No | Yes |
Element interaction by ID | No | No | No | Yes |
State diffs | No | No | No | Yes |
Semantic (a11y tree) | No | Partial | No | Yes |
No pixels, no rendering | No | Yes | No | Yes |
Zero cost (runs locally) | Yes | Yes | Yes | Yes |
Related MCP server: @playwright/mcp
Install
npm install -g webpilot-cli
npx playwright install chromium # one-time browser setupQuick Start
# Interactive REPL
wpilot https://google.com
# JSON output for LLM agents
wpilot --agent https://google.com
# Pipe mode for scripting
echo 'goto https://example.com
extract --links' | wpilot --pipe
# Shorthand URLs
wpilot :3000 # → http://localhost:3000
wpilot google.com # → https://google.comMCP Server (for Claude, ChatGPT, etc.)
Webpilot ships as an MCP server — any LLM agent that supports the Model Context Protocol can browse the web through it.
Setup with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"webpilot": {
"command": "npx",
"args": ["-y", "webpilot-cli", "--mcp"]
}
}
}Setup with VS Code / Copilot
Add to your .vscode/mcp.json:
{
"servers": {
"webpilot": {
"command": "npx",
"args": ["-y", "webpilot-cli", "--mcp"]
}
}
}Available MCP Tools
Tool | Description |
| Open a URL and get page state |
| Get current page as numbered elements |
| Click element by |
| Type into input/textarea by |
| Select dropdown option |
| Scroll up/down/top/bottom |
| Go back in history |
| Extract text, links, tables, forms, or metadata |
| Execute JavaScript in page context |
| Capture page as PNG image |
| List open tabs |
| Open new tab |
| Close browser session |
Example Agent Interaction
Agent: web_navigate("https://news.ycombinator.com")
→ 280 elements: [1] link "Hacker News", [2] link "new", [3] link "past" ...
Agent: web_click(5)
→ Navigated to article page, 42 elements
Agent: web_extract({ type: "text" })
→ Full article text extracted
Agent: web_back()
→ Back to Hacker News front pageCommands Reference
Command | Description |
| Navigate to URL |
| Click element by ID |
| Type into form field |
| Select dropdown option |
| Toggle checkbox / hover |
| Press keyboard key (Enter, Tab, etc.) |
| Browser history |
| Reload current page |
| Scroll the page |
| Search for text in elements |
| Re-display current page state |
| Extract structured content |
| Execute JavaScript |
| Save screenshot |
| View page HTML |
| Tab management |
| Show all commands |
Three Output Modes
Human (default) — Colored, formatted for terminal reading
Agent (
--agent) — JSON structured output for LLM consumptionPipe (auto-detected) — Plain text for
grep,awk, scripting
How It Works
Website → Playwright (headless Chromium) → CDP Accessibility Tree → Numbered Elements → YouPlaywright launches headless Chromium — full JS, cookies, SPAs, everything works
The accessibility tree is extracted via Chrome DevTools Protocol — semantic structure, not pixels
Elements get numbered IDs —
[1],[2],[3]... for easy targetingAfter each action, a state diff shows what changed, not the entire page
You interact with simple commands:
click [3],type [5] "hello"
Works With Everything
localhost:3000— your dev serverPublic websites — Google, GitHub, HN, anything
React / Next.js / Vue / Angular / Svelte — full JS execution
SPAs with client-side routing
Sites behind login — cookies persist in session
Dynamic content — JS runs before each snapshot
Forms, dropdowns, checkboxes — full interaction
Multi-tab browsing
Use Cases
LLM agents browsing the web — Claude/ChatGPT navigate, fill forms, extract data via MCP
E2E testing in CI — pipe commands, assert output, no flaky selectors
Web scraping — extract links, tables, text from any JS-rendered page
Accessibility auditing — see exactly what the a11y tree exposes
SSH/headless environments — browse from any terminal, no GUI needed
Development
git clone https://github.com/luckysolanki902/webpilot.git
cd webpilot
npm install
npx playwright install chromium
npm run build # → dist/index.js
npm run dev # Watch modeLicense
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/luckysolanki902/webpilot'
If you have feedback or need assistance with the MCP directory API, please join our Discord server