mcp_run_command_safely · Local Code MCP: Risk & Policy

WHAT IT DOES

What mcp_run_command_safely does on Local Code

AI agents invoke mcp_run_command_safely to trigger actions in Local 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.

WHY IT NEEDS A POLICY

Why mcp_run_command_safely needs a policy

Command execution is inherently an Execute category risk. Even though the tool applies allowlist and project-root controls to restrict what may run, it still triggers external operations whose effects depend on which commands are whitelisted. Blast radius depends on allowlist design, but misconfiguration or bypass could allow privilege escalation, lateral movement, or system compromise.

From the tool's definition Tool name contains 'run_command' and description states it 'Run[s] a command' — this is code/command execution.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mcp_run_command_safely Rate-limited

mcp_run_command_safely 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": {
    "mcp_run_command_safely": {
      "limits": [
        {
          "counter": "mcp_run_command_safely_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 Local Code, so you can run agents against it safely.

FAQ

Questions about mcp_run_command_safely

What does the mcp_run_command_safely tool do? +

Run a command only if it matches the configured allowlist and project root policy. It is categorised as a Execute tool in the Local Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcp_run_command_safely? +

Register the Local Code MCP server in PolicyLayer and add a rule for mcp_run_command_safely: 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 Local Code. Nothing to install.

What risk level is mcp_run_command_safely? +

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

Can I rate-limit mcp_run_command_safely? +

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

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

mcp_run_command_safely is provided by the Local Code MCP server (js190-prog/local-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.