Get step-by-step trace log for a CPI message (only available when trace is enabled on the iFlow).
AI agents call get_trace_log to retrieve information from Mcp Sap Cpi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic trace logs from SAP CPI messages, which is fundamentally a read operation with no side effects. However, severity is high rather than low because trace logs in an enterprise integration platform can contain sensitive data including message contents, credentials, API keys, and proprietary business logic flows.
From the tool's definition Tool name 'get_trace_log' and description 'Get step-by-step trace log for a CPI message' indicate retrieval of diagnostic logs without modification. The phrase 'trace log' confirms read-only query operation.
Attacks that exploit this kind of access
Get step-by-step trace log for a CPI message (only available when trace is enabled on the iFlow). It is categorised as a Read tool in the Mcp Sap Cpi MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sap Cpi MCP server in PolicyLayer and add a rule for get_trace_log: 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 Cpi. Nothing to install.
get_trace_log 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_trace_log 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_trace_log. 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_trace_log is provided by the Mcp Sap Cpi MCP server (keelside/mcp-sap-cpi). 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 →