AI agents call list_entity_relations to retrieve information from Orihime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs introspection of JPA entity relationships—a read-only operation that retrieves existing metadata from the codebase without creating, modifying, or deleting any data. It poses minimal risk as it only surfaces information about the code graph already indexed in KuzuDB. The blast radius of misuse is limited to information disclosure of application structure.
From the tool's definition Tool name 'list_entity_relations' and description 'List all JPA entity relationships in a repo' indicate a query/listing operation that retrieves metadata about code structure without modification.
Attacks that exploit this kind of access
List all JPA entity relationships in a repo. It is categorised as a Read tool in the Orihime MCP Server, which means it retrieves data without modifying state.
Register the Orihime MCP server in PolicyLayer and add a rule for list_entity_relations: 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 Orihime. Nothing to install.
list_entity_relations 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 list_entity_relations 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 list_entity_relations. 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.
list_entity_relations is provided by the Orihime MCP server (srinivasan-sundaresan95/orihime). 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 →