Load a locally saved draft snapshot by ID
AI agents call load_local_draft to retrieve information from Ice Puzzle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves an existing draft by ID from local storage. Loading data for inspection or use is a read operation. No data is created, modified, deleted, or executed. The severity is low because reading draft data poses minimal risk—the blast radius of accidental misuse is confined to information disclosure of the user's own design work.
From the tool's definition Tool description states 'Load a locally saved draft snapshot by ID' — this is a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Load a locally saved draft snapshot by ID. It is categorised as a Read tool in the Ice Puzzle MCP Server, which means it retrieves data without modifying state.
Register the Ice Puzzle MCP server in PolicyLayer and add a rule for load_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.
load_local_draft is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_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 load_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.
load_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 →