Set the player start position
AI agents use set_start 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 modifies level design data (player starting position) but does not execute code, delete data irreversibly, or move money. It is reversible—the start position can be changed again. Among the sibling tools (add_pushable_rock, add_thin_ice, add_warp_pair, clear_level, delete_draft), this aligns with the Write category of tools that modify level state.
From the tool's definition Tool name 'set_start' and description 'Set the player start position' indicate modification of level data. This is a write operation that creates or modifies game level configuration reversibly.
Attacks that exploit this kind of access
Set the player start position. 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 set_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 Ice Puzzle. Nothing to install.
set_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 set_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 set_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.
set_start 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 →