Get the screen and analyze its details.
AI agents call omniparser_details_on_screen to retrieve information from Omniparser Autogui without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes visual information from the screen without triggering any actions, modifications, or side effects. It is analogous to a screenshot or screen inspection capability, which is a passive Read operation. The sibling tools (click, drag, input_key, write, etc.) perform the actual GUI automation; this tool only observes state.
From the tool's definition Tool name includes 'details_on_screen' and description states 'Get the screen and analyze its details' — pure information retrieval with no modification or execution of commands.
Documented attack patterns abuse exactly the kind of access omniparser_details_on_screen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Omniparser Autogui, and nothing reaches the server without passing your rules. This is the rule we recommend for omniparser_details_on_screen:
{
"version": "1",
"default": "deny",
"tools": {
"omniparser_details_on_screen": {}
}
}omniparser_details_on_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 screen and analyze its details. It is categorised as a Read tool in the Omniparser Autogui MCP Server, which means it retrieves data without modifying state.
Register the Omniparser Autogui MCP server in PolicyLayer and add a rule for omniparser_details_on_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 Omniparser Autogui. Nothing to install.
omniparser_details_on_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 omniparser_details_on_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 omniparser_details_on_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.
omniparser_details_on_screen is provided by the Omniparser Autogui MCP server (non906/omniparser-autogui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Omniparser Autogui tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Omniparser Autogui tools catalogued and risk-classified — across an index of 42,500+ MCP servers.