Start a new scratchpad task/workspace.
AI agents use scratchpad_start to create or update resources in TTG Scratchpad MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TTG Scratchpad MCP Server environment.
This tool creates a new workspace/task, which is a Write operation (creating new data). It does not delete, execute code, or move money. The blast radius is medium since it creates isolated user environments with MongoDB storage and activity logging, but misuse is limited to resource creation rather than data loss or financial impact.
From the tool's definition Start a new scratchpad task/workspace
Attacks that exploit this kind of access
Start a new scratchpad task/workspace. It is categorised as a Write tool in the TTG Scratchpad MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TTG Scratchpad MCP Server MCP server in PolicyLayer and add a rule for scratchpad_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TTG Scratchpad MCP Server. Nothing to install.
scratchpad_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scratchpad_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scratchpad_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scratchpad_start is provided by the TTG Scratchpad MCP Server MCP server (mrgizmo212/scratchpad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →