mcpField
P
pilot-mcp — Fast Browser Automation MCP Server

pilot-mcp — Fast Browser Automation MCP Server

Local
github.com/TacosyHorchataBrowser Automation32Updated 18w ago

About pilot-mcp — Fast Browser Automation MCP Server

A browser automation MCP server for AI agents, using isolated in-process Playwright sessions by default. It suits QA automation and screenshot evidence, and keeps page snapshots small to limit context size.

Key features

  1. 01Isolated native Playwright browser sessions by default
  2. 02Tool profiles with 9, 40 or 69 tools
  3. 03Snapshot diffing that returns only changes
  4. 04Cookie import from local browsers
  5. 05Iframe support and handoff for CAPTCHAs

Use cases

  1. 01Running parallel QA automation with screenshot evidence
  2. 02Letting an AI agent open a page and summarize it
  3. 03Reusing a real Chrome profile through extension mode when logged-in state is needed

MCP support

This project is an MCP server that exposes browser operations such as navigate, click, fill, screenshot and snapshot diff as tools over stdio to MCP clients like Claude Code and Cursor.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"Pilot": {
"command": "npx",
"args": [
"-y",
"pilot-mcp"
]
}
}
}
Run commandnpx -y pilot-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmpilot-mcp

Tools

30

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
urlstringYesURL to navigate to (e.g., "https://example.com")

Details

From the project README

pilot — browser automation MCP for AI agents

npm license stars

Native Playwright-backed browser sessions by default. No Chrome extension required for QA automation.

pilot demo

Pilot has two browser backends:

  • Native mode (default): isolated Playwright browser contexts. This is the supported path for parallel QA automation and reliable screenshots.
  • Extension mode (legacy/opt-in): connects to your real Chrome profile when you need existing cookies and logged-in sessions.

Native mode avoids chrome.tabs.captureVisibleTab() entirely, so screenshots do not depend on Chrome being foregrounded, a tab being visibly active, or the extension service worker being fresh.


How it works

AI Agent → MCP Server → Broker on 127.0.0.1:3131 → Native browser session
         (stdio)       (first process owns broker)  (Playwright context/page)
  1. Pilot runs as an MCP server — Claude Code, Cursor, or any MCP client connects via stdio
  2. The first Pilot process becomes the broker on localhost
  3. Later Pilot processes connect as broker clients
  4. Each session gets an isolated native browser context/page
  5. Screenshots come from Playwright, not the Chrome extension capture API

Quick Start

1. Add the MCP server
codex mcp add pilot \
  --env PILOT_BROWSER_MODE=native \
  --env PILOT_PROFILE=full \
  -- npx -y pilot-mcp

For a local checkout:

npm install
npm run build
codex mcp add pilot \
  --env PILOT_BROWSER_MODE=native \
  --env PILOT_PROFILE=full \
  -- node /absolute/path/to/pilot/dist/index.js
2. Use it

"Open https://example.com, take a screenshot, and summarize the page."

No extension install. No Chrome foreground requirement.

For full native-mode operations, stress commands, and cleanup checks, see docs/native-mode.md.


Lean snapshots

Other tools dump 50K+ chars per page into your context window. Pilot keeps things small:

Other tools:   navigate(58K) → navigate(58K) → answer        = 116K chars
Pilot:         navigate(2K)  → navigate(2K)  → snapshot(9K)  =  13K chars

snapshot_diff shows only what changed between actions — no redundant re-reads.

Less context = faster responses, cheaper API calls, fewer hallucinations.


Pilot vs @playwright/mcp

Pilot@playwright/mcp
BrowserNative Playwright context by default; real Chrome via legacy extensionNew Chromium instance
Auth stateNative isolated by default; extension mode can use real Chrome cookiesAnonymous — manual setup
Bot detectionNative for automation; extension mode for real-profile handoffBlocked by Cloudflare
Snapshot size~2K navigate, ~9K full~50-60K
Snapshot diffpilot_snapshot_diff❌
Cookie importChrome, Arc, Brave, Edge, CometManual JSON
Iframes✅❌
Tool profilescore (9) / standard (40) / full (69)--caps groups
Transportstdiostdio, HTTP, SSE

69 tools across 3 profiles

LLMs degrade as tool lists grow. Load only what you need:

ProfileToolsWhat's included
core9navigate, snapshot, click, fill, type, press_key, wait, screenshot, snapshot_diff
standard40Core + pilot_act, pilot_guide, evidence, doctor/reset, tabs, scroll, hover, drag, iframes, auth, block, find
full69Standard + network intercept, assertions, clipboard, geolocation, CDP, evaluate, PDF, responsive, deep inspection
{
  "mcpServers": {
    "pilot": {
      "command": "npx",
      "args": ["-y", "pilot-mcp"],
      "env": { "PILOT_PROFILE": "standard" }
    }
  }
}

Default: standard. Full tool reference →


Native mode

Native mode is the default:

PILOT_BROWSER_MODE=native

Use it for QA automation, parallel MCP sessions, and screenshot evidence.

Verify it before QA runs:

PILOT_HEADLESS=1 npm run stress:screenshots
npm run stress:codex

Expected: both report 6/6 passed.

Extension mode

Extension mode is legacy and opt-in:

PILOT_BROWSER_MODE=extension

Use it only when you need a user's already-authenticated real Chrome profile.

Import cookies from your real browser: pilot_import_cookies({ browser: "chrome", domains: [".github.com"] })

Supports Chrome, Arc, Brave, Edge, Comet via macOS Keychain / Linux libsecret. For CAPTCHAs: pilot_handoff → you intervene → pilot_resume.


Requirements

  • Node.js >= 18
  • Playwright Chromium
  • macOS or Linux
  • Extension mode only: Chrome + Pilot extension

If Chromium is missing:

npx playwright install chromium

Security

  • Extension communicates on localhost only (127.0.0.1)
  • Native broker communicates on localhost only (127.0.0.1)
  • Native sessions use isolated browser contexts per MCP session
  • Output path validation prevents writes outside PILOT_OUTPUT_DIR
  • Path traversal protection on all file operations
  • PILOT_PROFILE controls which tools are exposed (core / standard / full)

Credits

Core architecture — ref-based element selection, snapshot diffing, annotated screenshots — ported from gstack by Garry Tan. Built on Playwright and the MCP SDK.


If Pilot is useful, star the repo — it helps others find it.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.