Leapfrog MCP Server
leapfrog-mcp
npm
v0.7.4
Published by anthonybono21-cloud — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Multi-session browser MCP for AI agents — 36 tools, stealth, persistent auth, code-first scripts, API sniffer, agent intelligence
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 10
high Tool "add_init_script" exposes command/code executionMTC-CAP-001
Tool "add_init_script" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool add_init_script
high Tool "execute" exposes command/code executionMTC-CAP-001
Tool "execute" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute
high Dynamic code execution in server code (dist/recording.js)MTC-SRC-001
In the server's implementation (`dist/recording.js:896`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const fn = new Function("page", "context", `return (async () => { ${script} })()`); await fn(pa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/recording.js
high Shell/command execution in server code (dist/script-executor.js)MTC-SRC-002
In the server's implementation (`dist/script-executor.js:18`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rocess", "fs", "child_process", "net", "http", "https", "global", "globalThis", ]; // ─── He
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/script-executor.js
high Shell/command execution in server code (dist/tile-manager.js)MTC-SRC-002
In the server's implementation (`dist/tile-manager.js:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from "child_process"; import { logger } from "./logger.js"; // ─── Tile Manager ──────────────────────
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tile-manager.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([api_discover]) co-exist with external-action tools ([network_log, add_init_script, execute]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [api_discover] → sinks [network_log, add_init_script, execute]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow api_discover → network_log
medium Unconstrained command parameter "script" on "add_init_script"MTC-CAP-006
Tool "add_init_script" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool add_init_script · inputSchema.properties.script
medium Unconstrained command parameter "script" on "execute"MTC-CAP-006
Tool "execute" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute · inputSchema.properties.script
low Mutating tool "add_init_script" declares no destructiveHintMTC-CAP-005
Tool "add_init_script" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool add_init_script
low Mutating tool "execute" declares no destructiveHintMTC-CAP-005
Tool "execute" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute
Tools 37
Each tool and what it can reach — statically extracted from the published source.
add_init_scriptruns code / shellapi_discoveringests untrusted inputexecuteruns code / shellnetwork_lognetwork egressactno sensitive capabilityapi_exportno sensitive capabilitybatch_actionsno sensitive capabilityconsole_logno sensitive capabilitydiffno sensitive capabilitydomain_knowledgeno sensitive capability
Show 27 more tools ↓
extractno sensitive capabilitynavigateno sensitive capabilitynetwork_interceptno sensitive capabilitypaginateno sensitive capabilitypool_statusno sensitive capabilityprofile_deleteno sensitive capabilityprofile_import_from_chromeno sensitive capabilityprofile_listno sensitive capabilityprofile_warmno sensitive capabilityscreenshotno sensitive capabilitysession_createno sensitive capabilitysession_create_batchno sensitive capabilitysession_destroyno sensitive capabilitysession_exportno sensitive capabilitysession_export_traceno sensitive capabilitysession_healthno sensitive capabilitysession_listno sensitive capabilitysession_list_profilesno sensitive capabilitysession_memoryno sensitive capabilitysession_replayno sensitive capabilitysession_save_profileno sensitive capabilitysnapshotno sensitive capabilitytab_closeno sensitive capabilitytab_switchno sensitive capabilitytabs_listno sensitive capabilitywait_forno sensitive capabilitywait_for_humanno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (37 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.7.4 latest |
A 93/100 | 10 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan leapfrog-mcp --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand