Get access to a specific game. Requires a valid day pass or will initiate payment.
AI agents use get_game to commit financial operations through Sphere MCP Gaming Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool's primary action may initiate a financial transaction (purchasing a day pass) via the Nostr protocol and Unicity blockchain payment system. Since it can commit financial obligations, it falls under the Financial category, which is the most severe applicable. Misuse by an AI agent could result in unauthorized purchases on behalf of the user.
From the tool's definition 'Requires a valid day pass or will initiate payment' — the tool can trigger a payment transaction if no valid pass exists.
Attacks that exploit this kind of access
Get access to a specific game. Requires a valid day pass or will initiate payment. It is categorised as a Financial tool in the Sphere MCP Gaming Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Sphere MCP Gaming Server MCP server in PolicyLayer and add a rule for get_game: 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 Sphere MCP Gaming Server. Nothing to install.
get_game is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the get_game 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 get_game. 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.
get_game is provided by the Sphere MCP Gaming Server MCP server (mastap/unicity-mcp-gaming). 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 →