// SCAN REPORT

MCPretentious

9 tools. 5 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

5 can modify or destroy data

4 read-only

9 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCPretentious ↓

TOOL MAP

What MCPretentious exposes to your agents

Read (4) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCPretentious tools

Destructive · High mcpretentious-close Closing a terminal window is an irreversible action that terminates running processes, destroys session state, and loses any unsaved work in that terminal. Execute · High mcpretentious-mouse This tool sends mouse input to a live terminal session, triggering arbitrary UI interactions and potentially executing commands or clicking UI elements. Execute · High mcpretentious-open Opening a new terminal window/session is an Execute-level action because it spawns an external process and creates infrastructure (a tracked session) that can be used to run arbitrary commands. Execute · Critical mcpretentious-type Sending keystrokes to a terminal is effectively arbitrary command execution.

5 of MCPretentious's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCPretentious

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

Deny destructive operations

{
  "mcpretentious-close": {
    "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

{
  "mcpretentious-resize": {
    "limits": [
      {
        "counter": "mcpretentious-resize_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "mcpretentious-info": {
    "limits": [
      {
        "counter": "mcpretentious-info_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 MCPretentious — 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 MCPRETENTIOUS →

Free to start. No card required.

FULL CATALOGUE

All 9 MCPretentious tools

DESTRUCTIVE 1 tools

Destructive mcpretentious-close Closes the terminal window associated with the specified terminal ID.

EXECUTE 3 tools

Execute mcpretentious-mouse Send mouse events to a terminal using SGR mouse protocol. This tool provides direct control over mous Execute mcpretentious-open Opens a new terminal window and creates a tracked terminal session. Returns a terminal ID that can be used wit Execute mcpretentious-type Send text and keystrokes to a terminal. Always pass as array. Examples: [

WRITE 1 tools

Write mcpretentious-resize Resizes a terminal to the specified dimensions in columns × rows.

READ 4 tools

Read mcpretentious-info Gets terminal metadata including dimensions (columns × rows) and session information. Read mcpretentious-list Lists all currently open terminal sessions with their IDs. Read mcpretentious-read Reads text output from a terminal session. Returns the current screen contents. Use mcpretentious-screenshot f Read mcpretentious-screenshot Takes a token-optimized screenshot of the terminal screen using a layered format that reduces token usage by 8

FAQ

Questions about MCPretentious

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

Yes. The MCPretentious server exposes 1 destructive tools including mcpretentious-close. 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 MCPretentious? +

The MCPretentious server has 1 write tools including mcpretentious-resize. 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 MCPretentious.

How many tools does the MCPretentious MCP server expose? +

9 tools across 2 categories: Read, Write. 4 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on MCPretentious? +

Register the MCPretentious 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 MCPretentious tool call.

Deterministic rules across all 9 MCPretentious tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCPRETENTIOUS →

Free to start. No card required.

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