submit_deploy_input · Remote Demo MCP: Risk & Policy

WHAT IT DOES

What submit_deploy_input does on Remote Demo MCP

AI agents invoke submit_deploy_input to trigger actions in Remote Demo MCP. 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 submit_deploy_input needs a policy

This tool submits authentication credentials (OTP/password) to advance an active deployment session. It is a step in the broader rsync-based deployment pipeline that pushes files to remote hosts. While it doesn't directly transfer files itself, it triggers progression of an external operation (remote deployment) by completing authentication, making it Execute.

From the tool's definition Submit OTP/password to an active deploy session... 向活动部署会话提交 OTP/密码输入

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

submit_deploy_input Rate-limited

submit_deploy_input 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": {
    "submit_deploy_input": {
      "limits": [
        {
          "counter": "submit_deploy_input_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 Remote Demo MCP, so you can run agents against it safely.

FAQ

Questions about submit_deploy_input

What does the submit_deploy_input tool do? +

Submit OTP/password to an active deploy session. Always call poll_deploy_session next unless nextAction=done in response. 向活动部署会话提交 OTP/密码输入。提交后通常下一步调用 poll_deploy_session，除非返回 nextAction=done。. It is categorised as a Execute tool in the Remote Demo MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on submit_deploy_input? +

Register the Remote Demo MCP server in PolicyLayer and add a rule for submit_deploy_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 Remote Demo MCP. Nothing to install.

What risk level is submit_deploy_input? +

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

Can I rate-limit submit_deploy_input? +

Yes. Add a rate_limit block to the submit_deploy_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 submit_deploy_input completely? +

Set action: deny in the PolicyLayer policy for submit_deploy_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 submit_deploy_input? +

submit_deploy_input is provided by the Remote Demo MCP server (jake-bcn/remote-demo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.