fd_exec · Fd MCP: Risk & Policy

WHAT IT DOES

What fd_exec does on Fd

AI agents invoke fd_exec to trigger actions in Fd. 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 fd_exec needs a policy

This tool allows execution of shell commands on bulk file selections, which can perform side effects dependent on the command arguments and target files. While it does not irreversibly delete data by itself (which would be Destructive), it enables arbitrary command execution with potential for unintended consequences.

From the tool's definition Tool description explicitly states 'Execute commands on multiple files' and 'faster & safer than find -exec'. The capability to run arbitrary commands on matched files makes this an Execute tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fd_exec Rate-limited

fd_exec 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": {
    "fd_exec": {
      "limits": [
        {
          "counter": "fd_exec_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 Fd, so you can run agents against it safely.

FAQ

Questions about fd_exec

What does the fd_exec tool do? +

⚙️ FAST BULK OPERATIONS: Execute commands on multiple files (faster & safer than find -exec). It is categorised as a Execute tool in the Fd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fd_exec? +

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

What risk level is fd_exec? +

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

Can I rate-limit fd_exec? +

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

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

fd_exec is provided by the Fd MCP server (thhart/fd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.