AI agents call check_released_api 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 tool retrieves and queries metadata about ABAP repository objects (DB tables, CDS views, function modules, classes, interfaces). It performs static analysis and lookup operations without creating, modifying, deleting, or executing code. The 'check' verb in this context means 'verify/inspect' rather than 'execute' or 'modify'.
From the tool's definition Tool name 'check_released_api' and description 'Look up ABAP repository objects' indicate a query/retrieval operation. The verb 'look up' and the context of checking repository metadata are passive information retrieval with no modification or execution.
Attacks that exploit this kind of access
Look up ABAP repository objects (DB tables, CDS view entities, function modules, classes, interfaces, …) in. 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 check_released_api: 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.
check_released_api 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 check_released_api 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 check_released_api. 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.
check_released_api 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 →