rpc_call · Rpcclient MCP: Risk & Policy

WHAT IT DOES

What rpc_call does on Rpcclient

AI agents invoke rpc_call to trigger actions in Rpcclient. 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 rpc_call needs a policy

This tool allows execution of generic RPC calls against a connected iOS device via rpcclient. While individual RPC calls may be benign, the generic nature ('arbitrary path call') means an AI agent could invoke any available RPC method—potentially launching apps, modifying settings, exfiltrating data, or performing privileged actions depending on what the iOS RPC server exposes.

From the tool's definition Tool name 'rpc_call' combined with description 'Execute a generic rpcclient path call against the session's root client object' explicitly indicates execution of arbitrary RPC calls. The word 'Execute' in the description is direct evidence.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rpc_call Rate-limited

rpc_call 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": {
    "rpc_call": {
      "limits": [
        {
          "counter": "rpc_call_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 Rpcclient, so you can run agents against it safely.

FAQ

Questions about rpc_call

What does the rpc_call tool do? +

Execute a generic rpcclient path call against the session's root client object. It is categorised as a Execute tool in the Rpcclient MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rpc_call? +

Register the Rpcclient MCP server in PolicyLayer and add a rule for rpc_call: 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 Rpcclient. Nothing to install.

What risk level is rpc_call? +

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

Can I rate-limit rpc_call? +

Yes. Add a rate_limit block to the rpc_call 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 rpc_call completely? +

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

rpc_call is provided by the Rpcclient MCP server (appknox/rpcclient-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.