// SCAN REPORT

TTG Scratchpad MCP Server

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

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

Last updated: 3 Jul 2026

8 can modify or destroy data

3 read-only

11 tools total

Community server · catalogue entry verified 03/07/2026

How to control TTG Scratchpad MCP Server ↓

TOOL MAP

What TTG Scratchpad MCP Server exposes to your agents

Read (3) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous TTG Scratchpad MCP Server tools

Destructive · High scratchpad_delete_file This tool permanently removes data (files) from the workspace with no undo mechanism. Write · Medium scratchpad_start This tool creates a new workspace/task, which is a Write operation (creating new data). Write · Low scratchpad_complete The tool creates or modifies data reversibly by updating task completion status within the scratchpad workspace. Write · Low scratchpad_demo The tool creates or populates sample/demo data in a scratchpad workspace, which is a reversible write operation.

8 of TTG Scratchpad MCP Server's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TTG Scratchpad MCP Server

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

Deny destructive operations

{
  "scratchpad_delete_file": {
    "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

{
  "scratchpad_complete": {
    "limits": [
      {
        "counter": "scratchpad_complete_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "scratchpad_list_files": {
    "limits": [
      {
        "counter": "scratchpad_list_files_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 TTG Scratchpad MCP 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 TTG SCRATCHPAD →

Instant setup, no code required.

FULL CATALOGUE

All 11 TTG Scratchpad MCP Server tools

DESTRUCTIVE 1 tools

Destructive scratchpad_delete_file Delete a file from the scratchpad workspace.

WRITE 6 tools

Write scratchpad_complete Mark a scratchpad task as complete. Write scratchpad_demo Demo the scratchpad widget with sample data. Write scratchpad_open_workspace Open/switch to a specific workspace by ID. Write scratchpad_start Start a new scratchpad task/workspace. Write scratchpad_update scratchpad_update Write scratchpad_write_file Write content to a file in the scratchpad workspace.

READ 3 tools

Read scratchpad_list_files List all files in the current scratchpad workspace. Read scratchpad_list_workspaces scratchpad_list_workspaces Read scratchpad_read_file Read content from a file in the scratchpad workspace.

OTHER 1 tools

Other my_tool my_tool

EXPLORE

Related servers

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

FAQ

Questions about TTG Scratchpad MCP Server

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

Yes. The TTG Scratchpad MCP Server server exposes 1 destructive tools including scratchpad_delete_file. 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 TTG Scratchpad MCP Server? +

The TTG Scratchpad MCP Server server has 6 write tools including scratchpad_complete, scratchpad_demo, scratchpad_open_workspace. 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 TTG Scratchpad MCP Server.

How many tools does the TTG Scratchpad MCP Server MCP server expose? +

11 tools across 4 categories: Destructive, Execute, Read, Write. 3 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on TTG Scratchpad MCP Server? +

Register the TTG Scratchpad MCP 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 TTG Scratchpad MCP Server tool call.

Deterministic rules across all 11 TTG Scratchpad MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TTG SCRATCHPAD →

Instant setup, no code required.

11 TTG Scratchpad MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.