AI agents invoke simulate_command to trigger actions in Claude Code. 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.
Despite the word 'simulates', this tool is described as executing/running commands, which falls under Execute. The actual behavior depends on implementation — 'simulate' may mean dry-run or may actually run the command. Given the server context (claude-code-mcp with tools like edit_code, fix_code), this likely involves real command execution or close approximation.
From the tool's definition Simulates the execution of a given command
Documented attack patterns abuse exactly the kind of access simulate_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code, and nothing reaches the server without passing your rules. This is the rule we recommend for simulate_command:
{
"version": "1",
"default": "deny",
"tools": {
"simulate_command": {
"limits": [
{
"counter": "simulate_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}simulate_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.
Free to start. No card required.
Simulates the execution of a given command. It is categorised as a Execute tool in the Claude Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Code MCP server in PolicyLayer and add a rule for simulate_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 Claude Code. Nothing to install.
simulate_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the simulate_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.
Set action: deny in the PolicyLayer policy for simulate_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.
simulate_command is provided by the Claude Code MCP server (kunihiros/claude-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Claude Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.