MCP.Market

Leapfrog MCP server

by anthonybono21-cloud·io.github.anthonybono21-cloud/leapfrog·v0.7.4·5 stars
No reviews yet

Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.

B71/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B71/100

full report

Adoption
New

5 stars

Reviews

Write one

Nobody has reviewed Leapfrog yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Leapfrog tools (37, 6 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • act

    Perform a browser interaction: click, fill, type, check, select, press key, scroll, hover, mousemove, drag, upload, resize, back, forward.

  • add_init_script

    Inject JavaScript that runs before every page load in a session.

  • api_discover

    List JSON APIs the page has called. Captured automatically from XHR/fetch traffic.

  • api_export

    Generate an OpenAPI v3 spec from observed API traffic.

  • batch_actionswrite action

    Execute multiple browser actions sequentially in a single MCP call.

  • console_log

    View captured browser console messages (log, warn, error, info, debug).

  • diff

    Compare the current page state against the last snapshot for this session.

  • domain_knowledge

    Inspect what Leapfrog has learned about a website from previous visits.

  • executewrite action

    Run a Playwright script with access to { page, context }. One tool call replaces 5-20 sequential MCP round trips.

  • extract

    Extract data from the page without a full snapshot.

  • navigate

    Navigate to a URL and return a compact accessibility snapshot with @eN refs.

  • network_intercept

    Add or remove network intercept rules.

  • network_log

    View captured HTTP requests/responses for a session.

  • paginate

    Extract data across multiple pages in a single call. Handles click-next, infinite scroll, and URL-pattern pagination.

  • pool_status

    Show pool stats, resource usage (memory, uptime), and all active session summaries. Shows per-session idle time. Sessions approaching 30-minute idle timeout should be refreshed or saved.

  • profile_deletewrite action

    Delete a saved persistent browser profile and all its data.

  • profile_import_from_chrome

    Connect to your real Chrome browser via CDP, capture its auth cookies, and save them

  • profile_list

    List saved persistent browser profiles with their auth status.

  • profile_warm

    Warm up a browser profile by browsing trusted sites (Google, Wikipedia, YouTube).

  • screenshot

    Capture a screenshot of the current page. Returns the image inline as base64. Optionally save to disk with savePath.

  • session_createwrite action

    Create a new isolated browser session with its own cookies and state.

  • session_create_batchwrite action

    Create multiple isolated browser sessions concurrently — 5-10x faster than sequential session_create calls.

  • session_destroywrite action

    Close and clean up a browser session. Frees a pool slot.

  • session_export

    Export session action history as a replayable recording.

  • session_export_trace

    Export a Playwright trace file for a session. Requires LEAP_TRACE=true.

  • session_health

    Check if a session is healthy (browser connected, page responsive).

  • session_list

    List all active browser sessions with their URLs and idle times.

  • session_list_profiles

    List all saved authentication profiles.

  • session_memory

    Recall what actions were performed in this session.

  • session_replay

    Replay a recording in the current session. Executes each step directly against the browser.

  • session_save_profile

    Save a session's cookies and auth state to disk.

  • snapshot

    Re-snapshot the current page for fresh @eN refs.

  • tab_close

    Close a tab by index. Defaults to the active tab. Cannot close the last remaining tab.

  • tab_switch

    Switch to a different tab by index. Use -1 to switch to the most recently opened tab (useful for popups).

  • tabs_list

    List all open tabs in a session. Shows index, URL, title, and which tab is active.

  • wait_for

    Wait for a condition before proceeding.

  • wait_for_human

    Pause and request human intervention. Shows the @..@ overlay with your reason.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

1 medium
  • Code scan69 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 172 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/recording.js: …quires script"); const fn = new Function("page", "context", `return (async () => …
Overall 71/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Leapfrog compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
71/100
higher than 36% of 866 Scraping and browsing servers
Tools
37
the typical Scraping and browsing server has 6
Tools that change things
16%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
5
more than 73% of 583 Scraping and browsing servers

What its tools let an agent do: 30 read · 1 create · 5 change · 1 run or deploy

Install Leapfrog in Claude Code, Cursor or VS Code

Runs npx -y leapfrog-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add leapfrog -- npx -y leapfrog-mcp
Add to Cursor

What the publisher says

From the Leapfrog repository's README, as published. We do not edit it. Read it on GitHub

Leapfrog 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

The Problem

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.

Quick Start

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:

  • Set LEAP_CHANNEL=chrome to use your installed Chrome/Chromium (recommended)
  • Or run npx playwright-core install chromium to install the bundled Chromium binary
  • Or set LEAPCDPENDPOINT to connect to an already-running Chrome instance

Feature Matrix

Stealth

Leapfrog ships 19 anti-detection patches enabled by default (LEAP_STEALTH=true). Four modes:

  • true (default) — all 19 patches active
  • passive — 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 before
  • false — no stealth patches

These cover the vectors that fingerprint services like CreepJS and fingerprint-pro actually check:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Leapfrog: common questions

Is Leapfrog MCP server safe?
Mostly: it is graded B (71/100). Read the Leapfrog safety report
How do I install Leapfrog?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Leapfrog need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Leapfrog maintained?
The last commit was 209 days ago (2026-04-09). The latest release is v0.7.4.
What can I use instead of Leapfrog?
Servers from other publishers that do the same job: Ghostfox MCP server, vibatchium MCP server and Stealthy Auto Browse MCP server.
How does Leapfrog compare with other Scraping and browsing MCP servers?
safety score 71/100 (higher than 36% of 866 Scraping and browsing servers); tools 37 (the typical Scraping and browsing server has 6); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Leapfrog

Same job from other publishers: the closest match first, then the best rated.

  • Ghostfox
    Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.
    A
  • vibatchium
    Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.
    A
  • Stealthy Auto Browse
    Self-hosted MCP server for stealth browser automation with human-like OS-level input.
    A
  • Browser Use
    Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
    A
  • Actionbook
    Let your AI agent operate any website through a real, logged-in browser session.
    A