AI agents call list_security_config 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 enumerate or retrieve security configuration data from the code knowledge graph. Despite the empty description lowering confidence slightly, the 'list_' prefix and context within a code analysis server strongly indicate a query/retrieval operation with no destructive or write side effects. Classified as Read unless evidence emerges of state modification or code execution.
From the tool's definition Tool name 'list_security_config' uses 'list' verb, which retrieves or queries data without modification. The empty description prevents verification of side effects, but the naming pattern matches other Read operations on this server (list_*, find_*).
Attacks that exploit this kind of access
list_security_config. 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_security_config: 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_security_config 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_security_config 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_security_config. 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_security_config 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 →