// SCAN REPORT

Rpcclient

24 tools. 16 can modify or destroy data without limits.

16 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

16 can modify or destroy data

8 read-only

24 tools total

Community server · catalogue entry verified 29/06/2026

How to control Rpcclient ↓

TOOL MAP

What Rpcclient exposes to your agents

Read (8) Write / Execute (16) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Rpcclient tools

Execute · High rpc_call This tool allows execution of generic RPC calls against a connected iOS device via rpcclient. Execute · High rpc_launch_app Launching an app is an Execute-category action because it triggers code/operations external to the MCP server itself (the iOS app), and the consequences depend on which app is launched and what that app does. Execute · High rpc_click_by_context This tool performs UI interaction (clicking) on an iOS device based on natural language intent. Execute · Medium rpc_click_label This tool performs a click action on a UI element in an iOS automation context.

16 of Rpcclient's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Rpcclient

PolicyLayer is an MCP gateway — it sits between your AI agents and Rpcclient, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "rpc_disconnect": {
    "limits": [
      {
        "counter": "rpc_disconnect_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ping": {
    "limits": [
      {
        "counter": "ping_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Rpcclient — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RPCCLIENT →

Instant setup, no code required.

FULL CATALOGUE

All 24 Rpcclient tools

EXECUTE 14 tools

Execute rpc_call Execute a generic rpcclient path call against the session's root client object. Execute rpc_click_by_context Click the most relevant screen element for a natural-language intent. Execute rpc_click_label Click a UI element by label (exact or fuzzy). Execute rpc_connect Create an rpcclient session to a remote rpcserver target. Execute rpc_dismiss_overlays Dismiss known transient overlays (for example Safari auth sheets). Execute rpc_fill_signin_credentials Fill sign-in credentials with support for app-stage or Safari-overlay-stage password entry. Execute rpc_handle_call Call a method or read callable attribute from a stored handle object. Execute rpc_launch_app Launch an app by bundle id or query; includes foreground verification result. Execute rpc_reconnect Reconnect an existing session to recover from broken transport; clears stale handles. Execute rpc_release_handle Release one stored object handle. Execute rpc_scroll Scroll using HID swipe gestures. Execute rpc_tap Tap by normalized screen coordinates, useful for focusing non-AX web fields. Execute rpc_type_focused_text Type text into the currently focused element (useful when Safari overlay fields are not AX-exposed). Execute rpc_type_text Type text by explicit label, semantic intent, or anchor-relative targeting.

WRITE 2 tools

Write rpc_disconnect Close and remove an existing rpcclient session. Write rpc_release_all_handles Release all stored object handles in a session.

READ 8 tools

Read ping Health check for the MCP server itself. Read rpc_capabilities Inspect client/subsystem API surface for a session. Read rpc_get_screen_context Return current primary app context and visible accessibility elements. Read rpc_handle_get Read an attribute from a stored handle object. Read rpc_list_apps List installed apps by fuzzy name/bundle matching. Read rpc_list_handles List object handles stored in a session. Read rpc_list_sessions List active rpcclient sessions. Read rpc_session_info Return metadata and current target info for a session.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Rpcclient

How do I prevent bulk modifications through Rpcclient? +

The Rpcclient server has 2 write tools including rpc_disconnect, rpc_release_all_handles. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Rpcclient.

How many tools does the Rpcclient MCP server expose? +

24 tools across 3 categories: Execute, Read, Write. 8 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on Rpcclient? +

Register the Rpcclient MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Rpcclient tool call.

Deterministic rules across all 24 Rpcclient tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RPCCLIENT →

Instant setup, no code required.

24 Rpcclient tools catalogued and risk-classified — across an index of 43,000+ MCP servers.