claude_code_command · Service Desk Plus MCP Server MCP

WHAT IT DOES

What claude_code_command does on Service Desk Plus MCP Server

AI agents invoke claude_code_command to trigger actions in Service Desk Plus MCP Server. 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 claude_code_command needs a policy

This tool executes arbitrary Claude Code commands, which is an external operation capable of triggering side effects. While the tool itself is on a Service Desk Plus MCP server, the ability to execute code commands makes it an Execute-category risk. The severity is high because code execution can lead to unintended outcomes depending on what commands are run.

From the tool's definition Tool name contains 'Execute' and description states 'Execute Claude Code commands', indicating it runs code or commands whose effects depend on the arguments provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claude_code_command Rate-limited

claude_code_command 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": {
    "claude_code_command": {
      "limits": [
        {
          "counter": "claude_code_command_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 Service Desk Plus MCP Server, so you can run agents against it safely.

FAQ

Questions about claude_code_command

What does the claude_code_command tool do? +

Execute Claude Code commands or get instructions for Claude Code integration. It is categorised as a Execute tool in the Service Desk Plus MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on claude_code_command? +

Register the Service Desk Plus MCP Server MCP server in PolicyLayer and add a rule for claude_code_command: 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 Service Desk Plus MCP Server. Nothing to install.

What risk level is claude_code_command? +

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

Can I rate-limit claude_code_command? +

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

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

claude_code_command is provided by the Service Desk Plus MCP Server MCP server (pttg-it/sdp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.