request_human_input · Dag Planner MCP: Risk & Policy

WHAT IT DOES

What request_human_input does on Dag Planner

AI agents invoke request_human_input to trigger actions in Dag Planner. 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 request_human_input needs a policy

This tool initiates an external blocking operation (halting task execution and awaiting human response), which is an action with side effects dependent on runtime arguments. It does not merely read data, nor does it write/delete data — it triggers an external workflow gate. Execute is the best fit since it affects the execution state of the DAG and causes an interaction with an external party (human approver).

From the tool's definition 'Request human input, blocking the task until decided' — triggers an external human-in-the-loop operation that pauses/blocks task execution until a human responds

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

request_human_input Rate-limited

request_human_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": {
    "request_human_input": {
      "limits": [
        {
          "counter": "request_human_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 Dag Planner, so you can run agents against it safely.

FAQ

Questions about request_human_input

What does the request_human_input tool do? +

Request human input, blocking the task until decided. It is categorised as a Execute tool in the Dag Planner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on request_human_input? +

Register the Dag Planner MCP server in PolicyLayer and add a rule for request_human_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 Dag Planner. Nothing to install.

What risk level is request_human_input? +

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

Can I rate-limit request_human_input? +

Yes. Add a rate_limit block to the request_human_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 request_human_input completely? +

Set action: deny in the PolicyLayer policy for request_human_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 request_human_input? +

request_human_input is provided by the Dag Planner MCP server (shubhamnegi/dag-planner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.