AI agents call chess_puzzles_random to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns chess puzzle data from Chess.com. It is a simple data retrieval operation (Read category). The blast radius of misuse is minimal: an AI agent could only fetch puzzles repeatedly, causing no harm to data, systems, or finances. Severity is low because retrieval tools pose limited security risk.
From the tool's definition Tool description states 'Get a random chess puzzle' — a retrieval operation with no side effects, state changes, or external impacts.
Attacks that exploit this kind of access
Get a random chess puzzle from Chess.com. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
Register the UnClick MCP server in PolicyLayer and add a rule for chess_puzzles_random: 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 UnClick. Nothing to install.
chess_puzzles_random 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 chess_puzzles_random 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 chess_puzzles_random. 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.
chess_puzzles_random is provided by the UnClick MCP server (@unclick/mcp-server). 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 →