// SCAN REPORT

Rn Debug

22 tools. 10 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

10 can modify or destroy data

12 read-only

22 tools total

Community server · catalogue entry verified 29/06/2026

How to control Rn Debug ↓

TOOL MAP

What Rn Debug exposes to your agents

Read (12) Write / Execute (10) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Rn Debug tools

Execute · Medium connect_app This tool initiates a connection to an external application and starts an ongoing process (log collection), triggering external operations beyond simple data retrieval. Execute · Medium press_back This tool triggers a navigation action (pressing the back button) on a connected app/device. Execute · Medium scroll This tool performs a UI interaction (swipe gesture) on a connected app/device, triggering an external operation that causes the screen to scroll. Execute · High tap This tool triggers a UI interaction (screen tap) on a connected app, which executes actions within the app depending on what element is at the given coordinates.

10 of Rn Debug's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Rn Debug

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

Rate limit write operations

{
  "close_session": {
    "limits": [
      {
        "counter": "close_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_connection_status": {
    "limits": [
      {
        "counter": "get_connection_status_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 Rn Debug — 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 RN DEBUG →

Instant setup, no code required.

FULL CATALOGUE

All 22 Rn Debug tools

EXECUTE 7 tools

Execute connect_app Connect to a running React Native app session on Android emulator or iOS simulator and start log collection. Execute press_back Trigger back navigation on the current platform. Execute reload_app Reload the active app session via Metro, with ADB fallback. Execute scroll Scroll screen content in a direction via swipe gesture. Execute tap Tap the screen at absolute coordinates. Final fallback only when testID and element-based targeting fail. Execute tap_element Tap a visible element by element id from get_visible_elements/get_ui_tree. Preferred fallback before coordinat Execute type_text Type text into the currently focused input field, with optional submit/enter key press.

WRITE 3 tools

Write close_session Close a specific session by sessionId. Write disconnect_app Disconnect the active React Native app session. Write set_active_session Set the active session used when sessionId is omitted.

READ 12 tools

Read get_connection_status Get current RN Inspector MCP session status and log buffer state. Read get_elements_by_test_id Find visible elements matching a React Native testID. Use exact first, then contains. If none, call get_screen Read get_errors Read buffered error and fatal logs using cursor-based pagination. Read get_logs Read buffered non-error logs using cursor-based pagination. Read get_network_requests Read buffered network request/response/error events using cursor-based pagination. Read get_screen_context Get inferred current Android screen context for remediation guidance. Use after testID lookup fails. Read get_screen_test_ids List testIDs present on the current screen with metadata. Start UI interaction flows with this tool before get Read get_test_id_remediation_plan Build deterministic patch/remediation guidance when a desired testID is missing. Recommended flow: get_screen_ Read get_ui_tree Read the current accessibility hierarchy from Android UIAutomator or iOS WDA. Read get_visible_elements Return flattened visible accessibility elements derived from the current UI tree. Use as fallback discovery af Read list_sessions List all active MCP device sessions. Read take_screenshot Capture a screenshot from the connected device.

FAQ

Questions about Rn Debug

How do I prevent bulk modifications through Rn Debug? +

The Rn Debug server has 3 write tools including close_session, disconnect_app, set_active_session. 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 Rn Debug.

How many tools does the Rn Debug MCP server expose? +

22 tools across 2 categories: Read, Write. 12 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Rn Debug? +

Register the Rn Debug 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 Rn Debug tool call.

Deterministic rules across all 22 Rn Debug tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RN DEBUG →

Instant setup, no code required.

22 Rn Debug tools catalogued and risk-classified — across an index of 43,000+ MCP servers.