run_command · MCP-Claude Code Bridge MCP: Risk & Policy

WHAT IT DOES

What run_command does on MCP-Claude Code Bridge

AI agents invoke run_command to trigger actions in MCP-Claude Code Bridge. 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 run_command needs a policy

Shell command execution is inherently an Execute-category risk because the outcome depends entirely on the argument (the command string). While not strictly destructive or financial by itself, it can trivially become either if the AI agent crafts malicious or unintended commands (e.g., `rm -rf /`, financial exfiltration scripts). The blast radius is maximal because shell access permits all forms of system compromise.

From the tool's definition Tool explicitly described as 'Run a shell command in the project directory' — this directly executes arbitrary code with the capability to modify, delete, or exfiltrate data depending on the command provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_command Rate-limited

run_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": {
    "run_command": {
      "limits": [
        {
          "counter": "run_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 MCP-Claude Code Bridge, so you can run agents against it safely.

FAQ

Questions about run_command

What does the run_command tool do? +

Run a shell command in the project directory. It is categorised as a Execute tool in the MCP-Claude Code Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_command? +

Register the MCP-Claude Code Bridge MCP server in PolicyLayer and add a rule for run_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 MCP-Claude Code Bridge. Nothing to install.

What risk level is run_command? +

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

Can I rate-limit run_command? +

Yes. Add a rate_limit block to the run_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 run_command completely? +

Set action: deny in the PolicyLayer policy for run_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 run_command? +

run_command is provided by the MCP-Claude Code Bridge MCP server (sobieskicodes/claude-desktop-mcp-to-claude-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.