get_class_source_mcp
AI agents call get_class_source_mcp to retrieve information from ADT MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ABAP class source code from a SAP system—a read-only operation with no side effects. However, severity is rated 'medium' rather than 'low' because source code access in enterprise SAP systems may expose sensitive business logic, credentials in comments, or proprietary algorithms, creating risk if an AI agent misuses access controls or exfiltrates code.
From the tool's definition Tool name 'get_class_source_mcp' and context indicating it retrieves source code from ABAP repository objects (similar sibling tools like 'get_function_source_mcp', 'get_cds_source_mcp').
Attacks that exploit this kind of access
get_class_source_mcp. It is categorised as a Read tool in the ADT MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ADT MCP Server MCP server in PolicyLayer and add a rule for get_class_source_mcp: 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 ADT MCP Server. Nothing to install.
get_class_source_mcp 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 get_class_source_mcp 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 get_class_source_mcp. 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.
get_class_source_mcp is provided by the ADT MCP Server MCP server (yahornovik/mcp-adt). 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 →