AI agents call snapshot_screen to retrieve information from PiloTY without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns the current state of a terminal screen without modifying, executing, or deleting anything. While it accesses terminal state (which could contain sensitive data in some contexts), the tool itself performs a passive information retrieval operation analogous to taking a screenshot.
From the tool's definition Tool description states it "Get[s] the current VT100-rendered terminal screen snapshot" — a read-only retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access snapshot_screen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PiloTY, and nothing reaches the server without passing your rules. This is the rule we recommend for snapshot_screen:
{
"version": "1",
"default": "deny",
"tools": {
"snapshot_screen": {}
}
}snapshot_screen is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the current VT100-rendered terminal screen snapshot. It is categorised as a Read tool in the PiloTY MCP Server, which means it retrieves data without modifying state.
Register the PiloTY MCP server in PolicyLayer and add a rule for snapshot_screen: 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 PiloTY. Nothing to install.
snapshot_screen is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the snapshot_screen 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 snapshot_screen. 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.
snapshot_screen is provided by the PiloTY MCP server (yiwenlu66/piloty). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 PiloTY tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 PiloTY tools catalogued and risk-classified — across an index of 42,500+ MCP servers.