Remove a game from the Lutris database (does not delete files)
AI agents call remove_game to permanently remove resources in Lutris MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a game from the Lutris database is an irreversible action that deletes a record. While files are preserved, the game entry, associated metadata, playtime statistics, and other attributes stored in the SQLite database are permanently removed. This cannot be simply reverted like a Write operation (update) would be.
From the tool's definition Tool name 'remove_game' combined with description 'Remove a game from the Lutris database' indicates irreversible deletion from the database.
Attacks that exploit this kind of access
Remove a game from the Lutris database (does not delete files). It is categorised as a Destructive tool in the Lutris MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lutris MCP Server MCP server in PolicyLayer and add a rule for remove_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 Lutris MCP Server. Nothing to install.
remove_game is a Destructive 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 remove_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 remove_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.
remove_game is provided by the Lutris MCP Server MCP server (praeses0/lutris-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 →