execute_service · Agentdesk MCP: Risk & Policy

WHAT IT DOES

What execute_service does on Agentdesk

AI agents invoke execute_service to trigger actions in Agentdesk. 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 execute_service needs a policy

This tool runs external services on the AgentDesk marketplace with user-supplied parameters. The effects are contingent on which service is selected and what arguments are provided, making it an Execute-class tool. Severity is high because arbitrary service execution on a third-party marketplace could have wide-ranging side effects depending on what services exist and how they are parameterized.

From the tool's definition Tool name 'execute_service' explicitly indicates execution. Description states 'Execute a service' and 'Pass service-specific input parameters,' indicating external operations are triggered whose effects depend on arguments provided by the caller.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_service Rate-limited

execute_service 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": {
    "execute_service": {
      "limits": [
        {
          "counter": "execute_service_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 Agentdesk, so you can run agents against it safely.

FAQ

Questions about execute_service

What does the execute_service tool do? +

Execute a service on the AgentDesk marketplace. Requires an AgentDesk API key for authentication. Pass service-specific input parameters. It is categorised as a Execute tool in the Agentdesk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_service? +

Register the Agentdesk MCP server in PolicyLayer and add a rule for execute_service: 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 Agentdesk. Nothing to install.

What risk level is execute_service? +

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

Can I rate-limit execute_service? +

Yes. Add a rate_limit block to the execute_service 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 execute_service completely? +

Set action: deny in the PolicyLayer policy for execute_service. 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 execute_service? +

execute_service is provided by the Agentdesk MCP server (rih0z/agentdesk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.