horoshop_call_api · Horoshop MCP: Risk & Policy

WHAT IT DOES

What horoshop_call_api does on Horoshop

AI agents invoke horoshop_call_api to trigger actions in Horoshop. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why horoshop_call_api needs a policy

This tool is a generic API executor that can invoke any Horoshop API endpoint with arbitrary parameters. Because it is unrestricted, it could perform reads, writes, deletions, financial transactions (e.g., order payments, refunds), or any other operation the Horoshop API supports.

From the tool's definition "Calls any Horoshop API function with arbitrary JSON parameters"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

horoshop_call_api Rate-limited

horoshop_call_api stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "horoshop_call_api": {
      "limits": [
        {
          "counter": "horoshop_call_api_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Horoshop, so you can run agents against it safely.

FAQ

Questions about horoshop_call_api

What does the horoshop_call_api tool do? +

Calls any Horoshop API function with arbitrary JSON parameters. It is categorised as a Execute tool in the Horoshop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on horoshop_call_api? +

Register the Horoshop MCP server in PolicyLayer and add a rule for horoshop_call_api: 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.

What risk level is horoshop_call_api? +

horoshop_call_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit horoshop_call_api? +

Yes. Add a rate_limit block to the horoshop_call_api 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.

How do I block horoshop_call_api completely? +

Set action: deny in the PolicyLayer policy for horoshop_call_api. 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.

What MCP server provides horoshop_call_api? +

horoshop_call_api 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.