AI agents call compare_abap to retrieve information from Abap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only analysis tool that performs a diff/comparison operation between two ABAP code versions and reports the results. It retrieves and presents information about changes without modifying the source code, executing operations, or causing side effects. The tool is purely analytical, similar to other static analysis tools on the server (lint_abap, check_cloud_readiness).
From the tool's definition The tool 'compare_abap' analyzes and reports differences between two versions of ABAP source code, examining 'what a rework actually changed' in terms of lint findings.
Attacks that exploit this kind of access
Compare a BEFORE and an AFTER version of ABAP source and report what a rework actually changed: lint findings. It is categorised as a Read tool in the Abap MCP Server, which means it retrieves data without modifying state.
Register the Abap MCP server in PolicyLayer and add a rule for compare_abap: 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.
compare_abap 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 compare_abap 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 compare_abap. 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.
compare_abap 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 →