AI agents invoke omniparser_scroll to trigger actions in Omniparser Autogui. 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 performs a physical GUI interaction (mouse scroll) that triggers external operations on the screen. While scrolling itself is relatively benign, it is an execution of a GUI action that could navigate interfaces, expose sensitive content, or be chained with other actions. It fits Execute as it performs real-world browser/desktop interactions rather than simply reading or writing data.
From the tool's definition 'mouse scrolling wheel behavior' on a server for 'Automatic operation of on-screen GUI'
Documented attack patterns abuse exactly the kind of access omniparser_scroll 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_scroll:
{
"version": "1",
"default": "deny",
"tools": {
"omniparser_scroll": {
"limits": [
{
"counter": "omniparser_scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniparser_scroll 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.
The mouse scrolling wheel behavior. It is categorised as a Execute tool in the Omniparser Autogui MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Omniparser Autogui MCP server in PolicyLayer and add a rule for omniparser_scroll: 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_scroll 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 omniparser_scroll 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_scroll. 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_scroll 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.