Discover MCPs & agents
Loading MCPs and agents…
Loading MCPs and agents…
Chrome extension + MCP server — AI agents control a tab in your real browser, already logged in
From the repo.
Native Playwright-backed browser sessions by default. No Chrome extension required for QA automation.

Pilot has two browser backends:
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.
AI Agent → MCP Server → Broker on 127.0.0.1:3131 → Native browser session
(stdio) (first process owns broker) (Playwright context/page)
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
"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.
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 | @playwright/mcp | |
|---|---|---|
| Browser | Native Playwright context by default; real Chrome via legacy extension | New Chromium instance |
| Auth state | Native isolated by default; extension mode can use real Chrome cookies | Anonymous — manual setup |
| Bot detection | Native for automation; extension mode for real-profile handoff | Blocked by Cloudflare |
| Snapshot size | ~2K navigate, ~9K full | ~50-60K |
| Snapshot diff | pilot_snapshot_diff | ❌ |
| Cookie import | Chrome, Arc, Brave, Edge, Comet | Manual JSON |
| Iframes | ✅ | ❌ |
| Tool profiles | core (9) / standard (40) / full (69) | --caps groups |
| Transport | stdio | stdio, HTTP, SSE |
LLMs degrade as tool lists grow. Load only what you need:
| Profile | Tools | What's included |
|---|---|---|
core | 9 | navigate, snapshot, click, fill, type, press_key, wait, screenshot, snapshot_diff |
standard | 40 | Core + pilot_act, pilot_guide, evidence, doctor/reset, tabs, scroll, hover, drag, iframes, auth, block, find |
full | 69 | Standard + 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 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 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.
If Chromium is missing:
npx playwright install chromium
PILOT_OUTPUT_DIRPILOT_PROFILE controls which tools are exposed (core / standard / full)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.
Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.
Tool
OS
Config file: ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"url": "{MCP_ENDPOINT_URL}"
}
}
}Paste into mcpServers in the config file. Restart Cursor after saving.
If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.