// SCAN REPORT

MCP Personal Assistant Agent

19 tools. 8 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

8 can modify or destroy data

11 read-only

19 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCP Personal Assistant Agent ↓

TOOL MAP

What MCP Personal Assistant Agent exposes to your agents

Read (11) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Personal Assistant Agent tools

Destructive · High delete_task The delete_task tool permanently removes a task without the ability to recover it. Execute · High control_device Controlling a smart home device executes real-world actions (e.g., locking/unlocking doors, turning on/off appliances, adjusting thermostats, disabling security systems). Write · Low add_task This tool creates a new task record, which is a write operation that modifies the task list state. Write · Low create_chart This tool creates a chart visualization from provided data points.

8 of MCP Personal Assistant Agent's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Personal Assistant Agent

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

Deny destructive operations

{
  "delete_task": {
    "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_task": {
    "limits": [
      {
        "counter": "add_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_device_state": {
    "limits": [
      {
        "counter": "get_device_state_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 Personal Assistant Agent — 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 PERSONAL ASSISTANT AGENT →

Free to start. No card required.

FULL CATALOGUE

All 19 MCP Personal Assistant Agent tools

DESTRUCTIVE 1 tools

Destructive delete_task Delete a task.

EXECUTE 1 tools

Execute control_device Control a smart home device.

WRITE 6 tools

Write add_task Add a new task. Write create_chart Create a chart from data points. Write create_event create_event Write create_scene Create a new scene with defined device states. Write send_email Send an email. Write update_task_status Update the status of a task.

READ 11 tools

Read get_device_state Get the current state of a smart home device. Read get_emails Get recent emails from a specific label. Read get_events Get upcoming calendar events. Read get_free_time Find free time slots in your calendar for a specific date. Read get_news Get latest news, optionally filtered by topic. Read get_weather Get current weather information for a location. Read list_devices List all available smart home devices. Read list_tasks List tasks with optional filtering by status. Read read_email Read the full content of a specific email. Read search_emails Search emails using Gmail search syntax. Read web_search Search the web for information.

EXPLORE

Related servers

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

FAQ

Questions about MCP Personal Assistant Agent

Can an AI agent delete data through the MCP Personal Assistant Agent MCP server? +

Yes. The MCP Personal Assistant Agent server exposes 1 destructive tools including delete_task. 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 Personal Assistant Agent? +

The MCP Personal Assistant Agent server has 6 write tools including add_task, create_chart, create_event. 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 Personal Assistant Agent.

How many tools does the MCP Personal Assistant Agent MCP server expose? +

19 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on MCP Personal Assistant Agent? +

Register the MCP Personal Assistant Agent 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 Personal Assistant Agent tool call.

Deterministic rules across all 19 MCP Personal Assistant Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP PERSONAL ASSISTANT AGENT →

Free to start. No card required.

19 MCP Personal Assistant Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.