send_cli_command · Betaflight MCP Server MCP: Risk & Policy

WHAT IT DOES

What send_cli_command does on Betaflight MCP Server

AI agents invoke send_cli_command to trigger actions in Betaflight MCP Server. 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 send_cli_command needs a policy

Sending raw CLI commands to a flight controller can execute arbitrary configuration changes, motor commands, or firmware operations. Misuse could result in dangerous drone behavior including uncontrolled motor activation, corrupted flight parameters, or loss of control — all with real-world physical safety implications. This is an Execute-category tool with critical severity due to the physical/safety blast radius.

From the tool's definition 'Send a raw CLI command to the flight controller' — executes arbitrary CLI commands on a safety-critical embedded system (FPV drone flight controller)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_cli_command Rate-limited

send_cli_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": {
    "send_cli_command": {
      "limits": [
        {
          "counter": "send_cli_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 Betaflight MCP Server, so you can run agents against it safely.

FAQ

Questions about send_cli_command

What does the send_cli_command tool do? +

Send a raw CLI command to the flight controller. It is categorised as a Execute tool in the Betaflight MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_cli_command? +

Register the Betaflight MCP Server MCP server in PolicyLayer and add a rule for send_cli_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 Betaflight MCP Server. Nothing to install.

What risk level is send_cli_command? +

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

Can I rate-limit send_cli_command? +

Yes. Add a rate_limit block to the send_cli_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 send_cli_command completely? +

Set action: deny in the PolicyLayer policy for send_cli_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 send_cli_command? +

send_cli_command is provided by the Betaflight MCP Server MCP server (jir13/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.