pilot-mcp — Fast Browser Automation MCP Server

Name: pilot-mcp — Fast Browser Automation MCP Server
Author: TacosyHorchata

@TacosyHorchata

About pilot-mcp — Fast Browser Automation MCP Server

Fast browser automation MCP server. In-process Playwright, 58 tools (profiles: 9/28/58), cookie import from Chrome/Arc/Brave, handoff/resume for CAPTCHAs, iframe support, snapshot diffing. 41% faster than @playwright/mcp.

#browser #automation #playwright #mcp #ai

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pilot": {
      "command": "npx",
      "args": [
        "-y",
        "pilot-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is pilot-mcp?

pilot-mcp is an MCP server that gives AI agents like Claude Code and Cursor a fast, persistent browser for web automation. Built on Playwright, it runs Chromium in-process over stdio, achieving ~5-50ms latency per action after the initial 3s launch — claimed to be 20x faster than alternatives.

How to use pilot-mcp?

Install with npx pilot-mcp and run npx playwright install chromium. Add a server entry to your Claude Code .mcp.json or Cursor MCP settings with command: "npx" and args: ["-y", "pilot-mcp"]. Environment variable PILOT_PROFILE selects tool set: core (9 tools), standard (25, default), or full (51 tools).

Key features of pilot-mcp

51 tools for navigation, snapshots, interaction, iframes, and debugging.
Snapshot‑by‑ref system: capture once, interact using @eN refs.
Token control: max_elements, structure_only, interactive_only filters.
Cookie import from Chrome, Arc, Brave, Edge, and Comet.
Handoff/resume: open headed Chrome, interact manually, then resume automation.
Snapshot diffing to track page changes between actions.

Use cases of pilot-mcp

Multi‑step web research: navigate, click, read results across several pages.
Form filling and data extraction with structured snapshots.
Testing UI workflows across tabs, iframes, and dialogs.
Comparing page content (staging vs production) via pilot_page_diff.
Debugging: inspect console logs, network requests, and element state in real time.

FAQ from pilot-mcp

What runtime does pilot-mcp require?

Node.js, Playwright, and Chromium (installed via npx playwright install chromium). No HTTP server or Chrome extension needed; everything runs over stdio.

How does pilot-mcp compare to @playwright/mcp or BrowserMCP?

pilot-mcp claims ~5-50ms per action vs 100-300ms for alternatives, with a persistent in‑process browser, 51 tools, cookie import, iframe support, and token‑control filters that alternatives lack.

Can I use my existing browser cookies?

Yes. pilot_import_cookies decrypts cookie databases from Chrome, Arc, Brave, Edge, and Comet using platform‑specific safe storage keys.

What security protections are built in?

Output path validation restricts screenshots/PDFs to PILOT_OUTPUT_DIR, path traversal is blocked, pilot_evaluate input is limited to 50KB, and file uploads resolve symlinks to prevent directory escape.

Does pilot-mcp support authentication?

No built‑in authentication. Cookie import can forward logged‑in sessions from your real browser, and custom headers (pilot_set_header) can be used for API keys or tokens.

Comments

More Browser Automation MCP servers

Apify Model Context Protocol (MCP) Server

apify

The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

1.7K