// SCAN REPORT

MCP Prompts Server

51 tools. 18 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

18 can modify or destroy data

33 read-only

51 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCP Prompts Server ↓

TOOL MAP

Read (33) Write / Execute (17) Destructive / Financial (1)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High delete_prompt This tool permanently removes data (a prompt) from the system without reversibility. Execute · High reset_esp32 This tool triggers a hardware reset on an ESP32 microcontroller device, which is an external operation with real-world effects. Execute · High android_launch_app Launching arbitrary apps on an Android device is an Execute action—it triggers external operations beyond the MCP server's direct control, with side effects determined by the launched application. Execute · High debug_session_start Debuggers like GDB and LLDB allow stepping through code, reading/modifying memory, executing arbitrary commands in the debugged process context, and invoking functions.

18 of MCP Prompts Server's 51 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MCP PROMPTS SERVER

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

Deny destructive operations

{
  "delete_prompt": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_prompt": {
    "limits": [
      {
        "counter": "add_prompt_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "aggregate_embedded_telemetry": {
    "limits": [
      {
        "counter": "aggregate_embedded_telemetry_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 MCP Prompts Server — 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 MCP PROMPTS →

Free to start. No card required.

ALL 51 MCP PROMPTS SERVER TOOLS

DESTRUCTIVE 1 tools

Destructive delete_prompt Delete a prompt

EXECUTE 12 tools

Execute reset_esp32 Reset the ESP32 device Execute android_launch_app Launch an app on Android device Execute debug_session_start Start a debugging session with GDB/LLDB Execute docker_exec_analysis Execute analysis tools in Docker containers Execute execute_cross_device_workflow Execute a workflow that coordinates multiple embedded devices Execute run_tests Execute tests with automatic framework detection Execute slash_command Execute a slash command to quickly apply a prompt template Execute workflow_execute Execute a multi-tool orchestrated workflow Execute android_play_sound Play a sound on Android device Execute android_show_toast Show a toast message on Android device Execute calibrate_esp32_sensors Calibrate ESP32 sensors Execute configure_esp32 Send configuration to ESP32 device

WRITE 5 tools

Write add_prompt add_prompt Write apply_template Apply variables to a prompt template Write create_prompt Create a new prompt Write set_android_clipboard Set clipboard content on Android device Write update_prompt Update an existing prompt

READ 33 tools

Read aggregate_embedded_telemetry Aggregate telemetry data from multiple embedded devices Read analyze_android_clipboard_patterns Analyze clipboard usage patterns using cognitive prompts Read analyze_changed_code Analyze code changes using git diff + static analysis Read analyze_code Perform unified static code analysis on source files Read analyze_embedded_patterns Analyze usage patterns across all embedded devices Read analyze_telemetry_patterns Analyze telemetry patterns using cognitive prompts Read android_take_screenshot Take a screenshot on Android device Read backup_embedded_data Backup data from all embedded devices Read discover_embedded_devices Discover all available embedded devices (ESP32, Android) Read emergency_embedded_shutdown Emergency shutdown of all embedded devices Read get_android_battery_status Get Android device battery status Read get_android_clipboard Get current clipboard content from Android device Read get_android_context Get contextual information about Android device state Read get_android_device_info Get Android device information and capabilities Read get_android_location Get Android device location data Read get_android_network_status Get Android device network status Read get_android_sensor_data Get Android device sensor data Read get_embedded_context Get contextual information about embedded device state Read get_embedded_device_status Get status overview of all embedded devices Read get_esp32_status Get current status and system information from ESP32 Read get_esp32_telemetry Get current telemetry data from ESP32 device Read get_prompt Get a prompt by ID Read get_stats get_stats Read get_telemetry_history Get historical telemetry data from ESP32 Read git_analyze_history Analyze git commit history for debugging insights Read list_prompts List prompts by category or get latest prompts Read list_slash_commands List available slash commands Read monitor_embedded_health Monitor health and status of all embedded devices Read predict_embedded_behavior Predict device behavior based on historical patterns Read search_prompts Search prompts by query Read suggest_slash_commands Get slash command suggestions based on a query Read sync_android_clipboard Synchronize clipboard across devices Read sync_clipboard_across_devices Synchronize clipboard content across all devices

RELATED SERVERS

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

FAQ

Can an AI agent delete data through the MCP Prompts Server MCP server? +

Yes. The MCP Prompts Server server exposes 1 destructive tools including delete_prompt. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP Prompts Server? +

The MCP Prompts Server server has 5 write tools including add_prompt, apply_template, create_prompt. 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 MCP Prompts Server.

How many tools does the MCP Prompts Server MCP server expose? +

51 tools across 4 categories: Destructive, Execute, Read, Write. 33 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on MCP Prompts Server? +

Register the MCP Prompts Server 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 MCP Prompts Server tool call.

Deterministic rules across all 51 MCP Prompts Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP PROMPTS →

Free to start. No card required.

51 MCP Prompts Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

MCP Prompts Server

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MCP PROMPTS SERVER

// ALL 51 MCP PROMPTS SERVER TOOLS

// RELATED SERVERS

// FAQ