AI agents use scaffold_rap_bo to create or update resources in Abap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Abap environment.
The tool generates (creates) ABAP RAP business object artifacts including CDS view entities and associated scaffolding code. This is a Write operation as it creates new code/artifacts. Since the server is described as 'offline' and operates without a live SAP system, the generated artifacts are likely files or code snippets rather than live system modifications, keeping severity at medium rather than high.
From the tool's definition Generate the complete, canonical RAP managed business-object stack for one root entity: root CDS view entity
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Generate the complete, canonical RAP managed business-object stack for one root entity: root CDS view entity,. It is categorised as a Write tool in the Abap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Abap MCP server in PolicyLayer and add a rule for scaffold_rap_bo: 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 Abap. Nothing to install.
scaffold_rap_bo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scaffold_rap_bo 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 scaffold_rap_bo. 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.
scaffold_rap_bo is provided by the Abap MCP server (abap-mcp). 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 →