send_pilot_agent_input · Helix Pilot MCP: Risk & Policy

WHAT IT DOES

What send_pilot_agent_input does on Helix Pilot

AI agents use send_pilot_agent_input to create or update resources in Helix Pilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Helix Pilot environment.

WHY IT NEEDS A POLICY

Why send_pilot_agent_input needs a policy

An AI agent can call send_pilot_agent_input faster than any human can review — one bad instruction and it creates or modifies resources in Helix Pilot by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_pilot_agent_input Rate-limited

send_pilot_agent_input stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_pilot_agent_input": {
      "limits": [
        {
          "counter": "send_pilot_agent_input_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Helix Pilot, so you can run agents against it safely.

FAQ

Questions about send_pilot_agent_input

What does the send_pilot_agent_input tool do? +

Continue an existing helix-pilot agent with a follow-up instruction. It is categorised as a Write tool in the Helix Pilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_pilot_agent_input? +

Register the Helix Pilot MCP server in PolicyLayer and add a rule for send_pilot_agent_input: 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 Helix Pilot. Nothing to install.

What risk level is send_pilot_agent_input? +

send_pilot_agent_input is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_pilot_agent_input? +

Yes. Add a rate_limit block to the send_pilot_agent_input 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_pilot_agent_input completely? +

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

send_pilot_agent_input is provided by the Helix Pilot MCP server (tsunamayo7/helix-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.