Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.
{
"mcpServers": {
"io-github-anthonybono21-cloud-leapfrog": {
"args": [
"-y",
"leapfrog-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.
Is it safe?
No known CVEs for leapfrog-mcp.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 1 days ago. 1 stars.
Will it work with my client?
Transport: stdio, sse. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'leapfrog-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for io.github.anthonybono21-cloud/leapfrog and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Multi-session browser MCP for AI agents.
36 tools. 15 parallel sessions. Stealth. HUD. Self-improvement. Up to 10x fewer tokens.
npm i leapfrog-mcp | Works with Claude Code, Cursor, Windsurf
Playwright MCP sends ~14,000 tokens for a content-heavy page like Hacker News. Most of that is noise. Your context window fills up. Your agent gets confused. You pay for it.
Leapfrog sends ~1,400 tokens. Same page. Same information. Up to 10x less noise.
┌─────────────────────────────────────────────────────┐
│ Playwright MCP │
│ ████████████████████████████████████████ ~14,000 │
│ │
│ Leapfrog │
│ █████ ~1,400 │
└─────────────────────────────────────────────────────┘
tokens per page (Hacker News, real test)
Savings range from 2-10x depending on page complexity. Content-heavy pages see the biggest wins. Dense forms see the smallest. The median across real-world sites is ~4-5x.
npx leapfrog-mcp --doctor # verify everything works
npx leapfrog-mcp --stealth-audit # test all 19 stealth patches
npx leapfrog-mcp --config # print MCP config to paste
Add to ~/.mcp.json (Claude Code) or your editor's MCP config:
{
"leapfrog": {
"command": "npx",
"args": ["-y", "leapfrog-mcp"],
"env": {
"LEAP_MAX_SESSIONS": "15",
"LEAP_TILE": "true",
"LEAP_HUD": "true",
"LEAP_AUTO_CONSENT": "true"
}
}
}
Leapfrog uses playwright-core (15MB) instead of playwright (1.6GB) and does not bundle a browser. Either:
LEAP_CHANNEL=chrome to use your installed Chrome/Chromium (recommended)npx playwright-core install chromium to install the bundled Chromium binaryLEAP_CDP_ENDPOINT to connect to an already-running Chrome instance| Leapfrog | Playwright MCP | agent-browser | |
|---|---|---|---|
| Tokens per page | ~1,200-2,500 | ~3,800-15,000 | ~300 |
| Parallel sessions | 15 | 1 | 1 |
| Session isolation | Yes | No | No |
| Multi-tab / popups | Yes | No | No |
| Network intercept | Yes | No | No |
| Console capture | Yes | Yes | No |
| Stealth / anti-bot | Yes | No | No |
| Smart wait (5 types) | Yes | Basic | No |
| Crash recovery | Yes | No | No |
| Batch actions (100/call) | Yes | No | No |
| Init script injection | Yes | Yes | No |
| Drag / upload / resize | Yes | Yes | No |
| Per-session proxy | Yes | No | No |
| Humanization (opt-in) | Yes | No | No |
| Auth profile reuse | Yes | No | No |
| Cookie persistence | Yes | No | No |
Leapfrog ships 19 anti-detection patches enabled by default (LEAP_STEALTH=true). Four modes:
true (default) — all 19 patches activepassive — removes automation signals only (webdriver, HeadlessChrome). Does NOT fake identity (WebGL, fonts, audio). Better for sites where trust matters more than evasion.auto — per-domain EXP3 bandit selects the optimal stealth configuration based on what's worked beforefalse — no stealth patchesThese cover the vectors that fingerprint services like CreepJS and fingerprint-pro actually check:
| Page classification (18) | Yes | No | No |
| Session memory | Yes | No | No |
| API intelligence | Yes | No | No |
| Adaptive wait + auto-retry | Yes | No | No |
| CAPTCHA auto-resolve | Yes | No | No |
| Self-improvement (9 dims) | Yes | No | No |
| Record / replay | Yes | No | No |
| Pagination extraction | Yes | No | No |
| Incremental snapshots (diff) | Yes | No | No |
| Stealth self-test CLI | Yes | No | No |
| SSRF protection | Yes | No | No |