Log inSubmit server
Leapfrog logo

Leapfrog

Runs isolated Chrome or Chromium browser sessions for agent automation, extraction, stealth, snapshots, and workflow replay.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Leapfrog

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "leapfrog": {
      "command": "npx",
      "args": [
        "-y",
        "leapfrog-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 37 tools correctly (1mo ago).

Overview

The leapfrog MCP server gives AI agents browser automation through up to 15 isolated parallel sessions. It uses playwright-core and can launch an installed Chrome or Chromium browser, connect to an existing Chrome instance, or install Chromium separately. Agents can navigate pages, interact with elements, capture focused snapshots, extract paginated content, and replay recorded workflows. Reach for it when browser tasks need session isolation, lower-noise page data, stealth controls, or multi-session operation.

Use cases

  • Automate authenticated browser workflows across isolated sessions
  • Extract content from paginated or infinite-scroll pages
  • Monitor pages with incremental snapshot differences
  • Replay recorded browser procedures with new parameters
  • Inspect browser actions with headed HUD overlays

Key features

  • Up to 15 isolated parallel browser sessions
  • 19 configurable stealth patches
  • Classified snapshots with incremental diffs
  • Pagination and infinite-scroll extraction
  • Session recording and replay
  • Adaptive navigation retry and session memory

Tools37

What Leapfrog lets your agent do. Expand a tool for its parameters.

Verified live~6.9k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

20/24 checks healthy over the last 91d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · leapfrog-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars5Stargazers on the source repository.
npm downloads242Package downloads in the last 30 days.
Last commit7mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed37Callable tools this server registers over MCP.
Directory activity6 viewsConfig copies, upvotes, and views on AllMCPs.

How Leapfrog works

What the leapfrog MCP server does

The leapfrog MCP server exposes browser automation for AI agents through MCP. It supports up to 15 parallel, isolated browser sessions, with multi-tab and popup handling, per-session proxy settings, persistent cookies, authentication profile reuse, and crash recovery. It is aimed at workflows where an agent needs to browse, interact with pages, monitor changes, or repeat a browser procedure.

Page output is designed to reduce irrelevant context. Navigation and snapshot operations classify pages into types such as login, article, dashboard, form, search results, checkout, and documentation. That classification influences which content and interactive elements are surfaced. The diff capability returns additions, removals, and changes since a previous snapshot, which suits polling and monitoring tasks.

How it works

The package runs with playwright-core, so it does not include a browser binary. It can use an installed Chrome or Chromium through LEAP_CHANNEL=chrome, connect to an already running browser through LEAP_CDP_ENDPOINT, or use a Chromium binary installed with npx playwright-core install chromium.

A session can use one of four stealth modes. The default enables 19 anti-detection patches; passive mode removes automation signals without changing browser identity details; auto mode selects configurations per domain based on prior results; and false disables stealth. Stealth can also be disabled for an individual session. Humanized mouse, typing, scrolling, pause, and fingerprint behavior is separate and opt-in because it adds latency.

Navigation includes fallback waiting strategies and can escalate stealth when a page appears blocked or challenged. The agent can disable automatic retries or set a maximum retry level. Session history records action outcomes, detects repeated action loops and bot redirects, and remains available through session_memory after context compression.

Setup and configuration

Install the package with npm or run it directly with npx. The diagnostic commands can check the environment, test the stealth patches, and print an MCP configuration:

  • npx leapfrog-mcp --doctor
  • npx leapfrog-mcp --stealth-audit
  • npx leapfrog-mcp --config

The MCP entry uses npx -y leapfrog-mcp as its command. Optional settings include LEAP_MAX_SESSIONS, LEAP_TILE, LEAP_HUD, and LEAP_AUTO_CONSENT. LEAP_STEALTH controls the stealth mode, while LEAP_HUMANIZE=true enables experimental humanized interaction. When running headed, LEAP_HUD=true adds visual action overlays to sessions.

Tools and capabilities

The leapfrog MCP server supports browser actions and workflow-oriented operations, including:

  • Creating and managing isolated sessions, tabs, and popups
  • Navigating pages and taking classified snapshots
  • Capturing snapshot differences for incremental monitoring
  • Performing batch actions, uploads, drag operations, and resizing
  • Intercepting network traffic and capturing console output
  • Extracting content through next-page controls, load-more buttons, infinite scroll, or URL patterns
  • Exporting session history as parameterized JSON or a Playwright script
  • Replaying recordings with parameter overrides and stop-or-skip error handling
  • Recalling session history with session_memory

Pagination extraction handles up to 50 pages and 100,000 total characters. Recordings can replace detected emails, passwords, and URLs with placeholders before reuse.

Limitations and notes

The package does not bundle a browser, so a usable Chrome, Chromium, CDP endpoint, or separately installed Chromium binary is needed. Humanization is experimental and increases latency. Stealth is configurable rather than mandatory, and sites can still block or challenge automated browsing. Automatic navigation retry can be disabled with autoRetry: false, and profile sessions are protected from the highest session-destruction escalation level.

The README reports approximate token reductions that vary by page complexity: content-heavy pages benefit more than dense forms. Pagination stops when it finds no further content, duplicate content, an empty page, or bot detection.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Leapfrog

leapfrog is an MCP server that connects AI agents to Chrome or Chromium browser sessions through Playwright. Its main tools support isolated session management, navigation, snapshots, browser actions, pagination extraction, incremental diffs, session memory, and recording replay. It can run up to 15 parallel sessions with configurable stealth and optional humanized interactions.

Install or run it with npm using `npm i leapfrog-mcp` or `npx -y leapfrog-mcp`. Use `npx leapfrog-mcp --config` to print an MCP configuration, then add the generated entry to your client configuration. Run `--doctor` to check the environment before connecting an agent.

Yes, leapfrog works with Cursor. The README also names Claude Code and Windsurf as supported clients. Configure the server with the `npx -y leapfrog-mcp` command in the client’s MCP settings.

No, the leapfrog MCP server does not bundle a browser. Set `LEAP_CHANNEL=chrome` to use an installed Chrome or Chromium browser, install Chromium with `npx playwright-core install chromium`, or set `LEAP_CDP_ENDPOINT` to connect to an existing Chrome instance.

Use its pagination extraction capability to follow next links, pagination controls, load-more buttons, infinite scroll, or URL page patterns in one tool call. Extraction is limited to 50 pages and 100,000 total characters and stops on duplicate content, empty pages, missing continuation controls, or bot detection.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewLeapfrog AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/leapfrog?style=directory)](https://allmcps.com/mcp/leapfrog)
HTML Embed
<a href="https://allmcps.com/mcp/leapfrog"><img src="https://allmcps.com/api/badge/leapfrog?style=directory" alt="Leapfrog on AllMCPs" /></a>