AI agents call find_complexity_hints 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.
The tool appears to retrieve or compute complexity metrics from the indexed code graph without modifying data or triggering external operations. The empty description lowers confidence slightly, but the consistent naming pattern across sibling tools and the 'find_' verb strongly indicate this is a query/analysis tool for reading code metrics rather than executing or modifying anything.
From the tool's definition Tool name 'find_complexity_hints' suggests querying/analyzing code metrics. No description provided, but the pattern matches sibling tools (find_callees, find_callers, find_entry_points) which are all Read operations that traverse the code knowledge graph.
Attacks that exploit this kind of access
find_complexity_hints. 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_complexity_hints: 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_complexity_hints 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_complexity_hints 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_complexity_hints. 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_complexity_hints 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 →