Multi-session browser MCP for AI agents — 36 tools, stealth, persistent auth, code-first scripts, API sniffer, agent intelligence
Most browser automation work still happens through a UI a human drives. Leapfrog MCP server moves it into the conversation instead. Multi-session browser MCP for AI agents — 36 tools, stealth, persistent auth, code-first scripts, API sniffer, agent intelligence.
leapfrog-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 7 tools. What each one is for:
network_log — See HTTP traffic — filter by URL, method, status, content-typeconsole_log — Read browser console output, filtered by levelnetwork_intercept — Block, mock, or log requests by URL patternapi_discover — List JSON APIs the page has called, classified by category (data, tracking, auth, cdn, ads)api_export — Generate an OpenAPI v3 spec from observed API trafficexecute — Run a Playwright script in a sandboxed environment — replaces 5-20 sequential MCP round tripssession_replay — Replay a recording in the current session with parameter overridesConfiguration is passed through the environment: LEAP_MAX_SESSIONS, LEAP_TILE, LEAP_HUD, LEAP_AUTO_CONSENT, LEAP_CAPTCHA_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
LEAP_CHANNEL=chrome) or install via npx playwright-core install chromiumPlenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Leapfrog's toolset — network_log, console_log, network_intercept and 4 more — is a fair guide to whether it matches your workflow. It is maintained by anthonybono21-cloud; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| network_log | See HTTP traffic — filter by URL, method, status, content-type |
| console_log | Read browser console output, filtered by level |
| network_intercept | Block, mock, or log requests by URL pattern |
| api_discover | List JSON APIs the page has called, classified by category (data, tracking, auth, cdn, ads) |
| api_export | Generate an OpenAPI v3 spec from observed API traffic |
| execute | Run a Playwright script in a sandboxed environment — replaces 5-20 sequential MCP round trips |
| session_replay | Replay a recording in the current session with parameter overrides |
{
"mcpServers": {
"leapfrog": {
"command": "npx",
"args": ["-y", "leapfrog-mcp"],
"env": {
"LEAP_MAX_SESSIONS": "your-value",
"LEAP_TILE": "your-value",
"LEAP_HUD": "your-value",
"LEAP_AUTO_CONSENT": "your-value",
"LEAP_CAPTCHA_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
LEAP_CHANNEL=chrome) or install via npx playwright-core install chromium| Variable | Description | Required |
|---|---|---|
| LEAP_MAX_SESSIONS | Configuration value read at startup. | Optional |
| LEAP_TILE | Configuration value read at startup. | Optional |
| LEAP_HUD | Configuration value read at startup. | Optional |
| LEAP_AUTO_CONSENT | Configuration value read at startup. | Optional |
| LEAP_CAPTCHA_API_KEY | Credential the server authenticates with. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.