act_input · Ruyipage MCP: Risk & Policy

WHAT IT DOES

What act_input does on Ruyipage

AI agents invoke act_input to trigger actions in Ruyipage. 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 act_input needs a policy

Given the server context (Firefox browser automation) and sibling tools like act_click and act_chain, act_input likely simulates keyboard input into web form fields or browser UI elements. This is an Execute-level action as it triggers external browser interactions. Severity is high because an AI agent could misuse this to input sensitive data, submit forms, or interact with web applications in unintended ways.

From the tool's definition Tool name 'act_input' on a browser automation server suggests inputting data into browser elements; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

act_input Rate-limited

act_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": {
    "act_input": {
      "limits": [
        {
          "counter": "act_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 Ruyipage, so you can run agents against it safely.

FAQ

Questions about act_input

What does the act_input tool do? +

act_input. It is categorised as a Execute tool in the Ruyipage MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on act_input? +

Register the Ruyipage MCP server in PolicyLayer and add a rule for act_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 Ruyipage. Nothing to install.

What risk level is act_input? +

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

Can I rate-limit act_input? +

Yes. Add a rate_limit block to the act_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 act_input completely? +

Set action: deny in the PolicyLayer policy for act_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 act_input? +

act_input is provided by the Ruyipage MCP server (neverl805/ruyipage_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.