AI agents call find_io_fanout 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 analyze I/O fan-out patterns in the code knowledge graph without modifying data. Sibling tools with 'find_' prefix are query/analysis tools. The empty description reduces confidence slightly, but the consistent naming pattern and server purpose (code indexing and analysis) strongly suggests this is a read-only query tool for extracting code structure information.
From the tool's definition Tool name 'find_io_fanout' suggests querying or identifying I/O operations and their fan-out patterns. The description is empty, but the server context indicates it exposes tools for 'call-flow tracing' and 'multi-hop taint analysis,' which are read-only code…
Attacks that exploit this kind of access
find_io_fanout. 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_io_fanout: 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_io_fanout 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_io_fanout 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_io_fanout. 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_io_fanout 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 →