Search commands by tag. Tags help identify commands for specific purposes (e.g.,
AI agents call hana_discover_by_tag to retrieve information from SAP HANA CLI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches or filters existing commands by tags—a read-only operation that retrieves information without side effects. It is analogous to listing or searching a catalog. No execution of commands, data modification, or deletion occurs; it merely helps discover which commands are available based on their tags.
From the tool's definition Tool name 'hana_discover_by_tag' and description 'Search commands by tag' indicate a query/retrieval operation with no data modification or execution capability.
Attacks that exploit this kind of access
Search commands by tag. Tags help identify commands for specific purposes (e.g.,. It is categorised as a Read tool in the SAP HANA CLI MCP Server, which means it retrieves data without modifying state.
Register the SAP HANA CLI MCP server in PolicyLayer and add a rule for hana_discover_by_tag: 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 SAP HANA CLI. Nothing to install.
hana_discover_by_tag 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 hana_discover_by_tag 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 hana_discover_by_tag. 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.
hana_discover_by_tag is provided by the SAP HANA CLI MCP server (hana-cli). 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 →