AI agents call horoshop_auth to retrieve information from Horoshop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs authentication and retrieves a token/metadata. It reads/fetches an auth token without creating, modifying, or deleting data. The main risk is credential exposure if misused, but the action itself is a read/fetch operation with no persistent side effects.
From the tool's definition Authenticates with Horoshop and returns token metadata
Attacks that exploit this kind of access
Authenticates with Horoshop and returns token metadata. It is categorised as a Read tool in the Horoshop MCP Server, which means it retrieves data without modifying state.
Register the Horoshop MCP server in PolicyLayer and add a rule for horoshop_auth: 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 Horoshop. Nothing to install.
horoshop_auth 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 horoshop_auth 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 horoshop_auth. 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.
horoshop_auth is provided by the Horoshop MCP server (narkov/horoshop-mcp-server). 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 →