serial_send · MCP Remote Access MCP: Risk & Policy

WHAT IT DOES

What serial_send does on MCP Remote Access

AI agents invoke serial_send to trigger actions in MCP Remote Access. 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 serial_send needs a policy

Sending data to a serial port triggers external operations on connected hardware (e.g., Raspberry Pi, embedded systems, IoT devices). The effects depend entirely on what data is sent — commands could reconfigure hardware, trigger actuators, flash firmware, or cause physical-world actions. This qualifies as Execute due to the external operation side effects whose impact depends on arguments.

From the tool's definition Send data to a serial port. Optionally wait for and return response.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

serial_send Rate-limited

serial_send 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": {
    "serial_send": {
      "limits": [
        {
          "counter": "serial_send_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 Remote Access, so you can run agents against it safely.

FAQ

Questions about serial_send

What does the serial_send tool do? +

Send data to a serial port. Optionally wait for and return response. It is categorised as a Execute tool in the MCP Remote Access MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on serial_send? +

Register the MCP Remote Access MCP server in PolicyLayer and add a rule for serial_send: 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 Remote Access. Nothing to install.

What risk level is serial_send? +

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

Can I rate-limit serial_send? +

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

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

serial_send is provided by the MCP Remote Access MCP server (rfingadam/mcp-remote-access). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.