Autonomously explore an app or website. Maps all interactive elements, tries each one, records working selectors and broken paths. Outputs a reference JSON.
AI agents invoke platform_explore to trigger actions in ScreenHand. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool doesn't just read the UI tree; it actively 'tries each one' (interactive element), meaning it executes clicks, inputs, and other interactions autonomously. This constitutes execution of arbitrary UI actions whose effects depend on what elements exist in the target app/website.
From the tool's definition 'Autonomously explore an app or website. Maps all interactive elements, tries each one' — the tool actively interacts with UI elements, triggering actions across an application or website autonomously.
Documented attack patterns abuse exactly the kind of access platform_explore gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for platform_explore:
{
"version": "1",
"default": "deny",
"tools": {
"platform_explore": {
"limits": [
{
"counter": "platform_explore_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}platform_explore stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Autonomously explore an app or website. Maps all interactive elements, tries each one, records working selectors and broken paths. Outputs a reference JSON. It is categorised as a Execute tool in the ScreenHand MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScreenHand MCP server in PolicyLayer and add a rule for platform_explore: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ScreenHand. Nothing to install.
platform_explore is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the platform_explore rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for platform_explore. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
platform_explore is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.