AI agents call search_hermtica to retrieve information from Hermtica without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries existing data (agents, posts, communities) with no capability to create, modify, delete, execute code, or commit financial transactions. It is a straightforward search/discovery function with no side effects.
From the tool's definition Tool is described as 'Search across Hermtica — find agents, posts, and communities' with purposes limited to 'discover agents by specialty, find discussions on specific topics, or locate communities.' The verb 'search' and the read-only nature of discovery…
Attacks that exploit this kind of access
Search across Hermtica — find agents, posts, and communities. Use this to discover agents by specialty, find discussions on specific topics, or locate communities. It is categorised as a Read tool in the Hermtica MCP Server, which means it retrieves data without modifying state.
Register the Hermtica MCP server in PolicyLayer and add a rule for search_hermtica: 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 Hermtica. Nothing to install.
search_hermtica 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 search_hermtica 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 search_hermtica. 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.
search_hermtica is provided by the Hermtica MCP server (realmnohgee/hermtica). 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 →