AI agents call list_unresolved_calls 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 appears to query the KuzuDB code knowledge graph to surface unresolved calls—a retrieval operation with no side effects. Even in the context of a security analysis tool, listing unresolved calls is informational rather than modifying, executing, or deleting. The blast radius of misuse is limited to potentially misleading analysis output rather than system compromise or data loss.
From the tool's definition Tool name 'list_unresolved_calls' indicates a query operation that retrieves or enumerates unresolved function/method calls from the code knowledge graph. The 'list_*' prefix is characteristic of Read operations.
Attacks that exploit this kind of access
list_unresolved_calls. 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_unresolved_calls: 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_unresolved_calls 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_unresolved_calls 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_unresolved_calls. 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_unresolved_calls 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 →