Create a new scratchpad in a workflow
AI agents use create-scratchpad to create or update resources in Scratchpad MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scratchpad MCP environment.
The tool creates a new data structure (scratchpad) within an existing workflow context. This is a reversible write operation with no side effects beyond adding a new artifact to the system. The blast radius is minimal as scratchpads are isolated collaboration artifacts. No destructive, execute, or financial implications.
From the tool's definition Tool name is 'create-scratchpad' and description states it 'Create a new scratchpad in a workflow', indicating data creation. Verb 'create' is explicitly listed as a Write category example. No deletion, code execution, or financial operations are implied.
Attacks that exploit this kind of access
Create a new scratchpad in a workflow. It is categorised as a Write tool in the Scratchpad MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scratchpad MCP server in PolicyLayer and add a rule for create-scratchpad: 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 Scratchpad MCP. Nothing to install.
create-scratchpad 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 create-scratchpad 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 create-scratchpad. 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.
create-scratchpad is provided by the Scratchpad MCP server (pc035860/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 →