Save a snapshot of the current draft in local MCP memory
AI agents use save_local_draft to create or update resources in Ice Puzzle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ice Puzzle environment.
This tool creates or stores data (a draft snapshot) in local memory, which is reversible—drafts can be overwritten, deleted, or replaced later. It does not execute arbitrary code, delete data, or move money. It is Write rather than Read because it modifies persistent state rather than merely querying it.
From the tool's definition save_local_draft saves a snapshot of the current draft, which modifies the state of the local MCP memory by persisting draft data.
Attacks that exploit this kind of access
Save a snapshot of the current draft in local MCP memory. It is categorised as a Write tool in the Ice Puzzle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ice Puzzle MCP server in PolicyLayer and add a rule for save_local_draft: 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 Ice Puzzle. Nothing to install.
save_local_draft 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 save_local_draft 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 save_local_draft. 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.
save_local_draft is provided by the Ice Puzzle MCP server (wmoten/ice-puzzle-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 →