Scroll the SAP GUI screen and return a screenshot of the resulting view
AI agents invoke sap_scroll to trigger actions in MCP SAP GUI Server. 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.
Scrolling is a browser/GUI action that manipulates the state of an external SAP GUI session. While scrolling itself doesn't modify data, it is an Execute-category action because it drives an external application's UI.
From the tool's definition 'Scroll the SAP GUI screen' — triggers a UI interaction (scrolling) within the SAP GUI application, which is an external system operation that changes the viewport state
Attacks that exploit this kind of access
Scroll the SAP GUI screen and return a screenshot of the resulting view. It is categorised as a Execute tool in the MCP SAP GUI Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP SAP GUI Server MCP server in PolicyLayer and add a rule for sap_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 MCP SAP GUI Server. Nothing to install.
sap_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 sap_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 sap_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.
sap_scroll is provided by the MCP SAP GUI Server MCP server (mario-andreschak/mcp-sap-gui). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →