AI agents call find_eager_fetches 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 retrieves and analyzes code metadata from the embedded KuzuDB knowledge graph to identify performance anti-patterns (N+1 queries). It performs read-only queries against indexed source code. No data is created, modified, deleted, or executed. Severity is low because misuse would result in false positives in performance analysis rather than system compromise or data loss.
From the tool's definition Tool name 'find_eager_fetches' and description 'Find all EAGER fetch relationships — potential N+1 query sources' indicate querying/analyzing code patterns without modifying, executing, or deleting data.
Attacks that exploit this kind of access
Find all EAGER fetch relationships — potential N+1 query sources. 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 find_eager_fetches: 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.
find_eager_fetches 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 find_eager_fetches 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 find_eager_fetches. 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.
find_eager_fetches 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 →