send_input_to_application · Cartesi Knowledge MCP Server MCP

WHAT IT DOES

What send_input_to_application does on Cartesi Knowledge MCP Server

AI agents use send_input_to_application to create or update resources in Cartesi Knowledge MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cartesi Knowledge MCP Server environment.

WHY IT NEEDS A POLICY

Why send_input_to_application needs a policy

An AI agent can call send_input_to_application faster than any human can review — one bad instruction and it creates or modifies resources in Cartesi Knowledge MCP Server by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_input_to_application Rate-limited

send_input_to_application 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_input_to_application": {
      "limits": [
        {
          "counter": "send_input_to_application_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 Cartesi Knowledge MCP Server, so you can run agents against it safely.

FAQ

Questions about send_input_to_application

What does the send_input_to_application tool do? +

Generate host-machine instructions for sending an input to a running Cartesi application through the InputBox using cast. It is categorised as a Write tool in the Cartesi Knowledge MCP Server 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_input_to_application? +

Register the Cartesi Knowledge MCP Server MCP server in PolicyLayer and add a rule for send_input_to_application: 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 Cartesi Knowledge MCP Server. Nothing to install.

What risk level is send_input_to_application? +

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

Can I rate-limit send_input_to_application? +

Yes. Add a rate_limit block to the send_input_to_application 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_input_to_application completely? +

Set action: deny in the PolicyLayer policy for send_input_to_application. 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_input_to_application? +

send_input_to_application is provided by the Cartesi Knowledge MCP Server MCP server (mugen-builders/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.