// MCP TOOL REFERENCE

LEAPFROG TOOLS

37 tools from the Leapfrog MCP Server, categorised by risk level.

View the Leapfrog policy → Token cost: 6,530 tokens →

// ALL 37 LEAPFROG TOOLS

READ 12 tools

Read api_discover List JSON APIs the page has called. Captured automatically from XHR/fetch traffic. Classifies into: data, t... Read console_log View captured browser console messages (log, warn, error, info, debug). Console capture starts automaticall... Read domain_knowledge Inspect what Leapfrog has learned about a website from previous visits. Shows stealth tier, wait strategy, ... Read extract Extract data from the page without a full snapshot. Types: text (visible text), html (markup), title, url, ... Read network_log View captured HTTP requests/responses for a session. Shows method, status, URL, size, and timing. Filter by... Read pool_status Show pool stats, resource usage (memory, uptime), and all active session summaries. Shows per-session idle ... Read profile_list List saved persistent browser profiles with their auth status. Read screenshot Capture a screenshot of the current page. Returns the image inline as base64. Optionally save to disk with ... Read session_list List all active browser sessions with their URLs and idle times. Read session_list_profiles List all saved authentication profiles. Read snapshot Re-snapshot the current page for fresh @eN refs. Use after 'act' when you need to re-orient, or scope to a ... Read tabs_list List all open tabs in a session. Shows index, URL, title, and which tab is active. New tabs (popups, OAuth ...

WRITE 17 tools

Write act Perform a browser interaction: click, fill, type, check, select, press key, scroll, hover, mousemove, drag,... Write add_init_script Inject JavaScript that runs before every page load in a session. Persists across navigations (Playwright bu... Write api_export Generate an OpenAPI v3 spec from observed API traffic. Navigate pages first to capture traffic, then export. Write diff Compare the current page state against the last snapshot for this session. Returns only what changed (addit... Write paginate Extract data across multiple pages in a single call. Handles click-next, infinite scroll, and URL-pattern p... Write profile_import_from_chrome Connect to your real Chrome browser via CDP, capture its auth cookies, and save them as a Leapfrog profile.... Write profile_warm Warm up a browser profile by browsing trusted sites (Google, Wikipedia, YouTube). Fresh profiles with zero ... Write session_create Create a new isolated browser session with its own cookies and state. Returns a short session ID (e.g. s_k3... Write session_create_batch Create multiple isolated browser sessions concurrently — 5-10x faster than sequential session_create calls.... Write session_export Export session action history as a replayable recording. Creates a JSON script from all mutating actions wi... Write session_export_trace Export a Playwright trace file for a session. Requires LEAP_TRACE=true. The trace can be viewed at trace.pl... Write session_health Check if a session is healthy (browser connected, page responsive). Omit sessionId to check all sessions. Q... Write session_memory Recall what actions were performed in this session. Useful after context window compression to recover lost... Write session_replay Replay a recording in the current session. Executes each step directly against the browser. Override {{plac... Write session_save_profile Save a session's cookies and auth state to disk. Use this after logging in to a site so future sessions can... Write tab_close Close a tab by index. Defaults to the active tab. Cannot close the last remaining tab. Returns a snapshot o... Write tab_switch Switch to a different tab by index. Use -1 to switch to the most recently opened tab (useful for popups). R...

DESTRUCTIVE 3 tools

Destructive network_intercept Add or remove network intercept rules. Block requests (ads, trackers), mock API responses, or log specific ... Destructive profile_delete Delete a saved persistent browser profile and all its data. Destructive session_destroy Close and clean up a browser session. Frees a pool slot.

EXECUTE 5 tools

Execute batch_actions Execute multiple browser actions sequentially in a single MCP call. Eliminates round-trip overhead for huma... Execute execute Run a Playwright script with access to { page, context }. One tool call replaces 5-20 sequential MCP round ... Execute navigate Navigate to a URL and return a compact accessibility snapshot with @eN refs. Refs like @e1, @e2 can be pass... Execute wait_for Wait for a condition before proceeding. Supports: element visible, text appears, network idle, URL navigati... Execute wait_for_human Pause and request human intervention. Shows the @..@ overlay with your reason. Use when you encounter a CAP...

// RUNNING THIS SERVER

The managed route: connect Leapfrog through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y leapfrog-mcp

// FAQ

How many tools does the Leapfrog MCP server have? +

The Leapfrog MCP server exposes 37 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Leapfrog tools? +

Route the Leapfrog server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Leapfrog tools fall into? +

Leapfrog tools are categorised as Read (12), Write (17), Destructive (3), Execute (5). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.