AI agents call list_decks to retrieve information from Codecks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists existing decks in the Codecks project management system with no side effects. It performs a simple enumeration/query of project structure data, fitting the Read category. The low severity reflects minimal blast radius—an AI agent misusing this would only retrieve information already accessible to the authenticated user, with no ability to modify, delete, or execute external actions.
From the tool's definition Tool name 'list_decks' and description 'List all decks' indicate a query operation that retrieves data without modification. The optional include_card_counts parameter is a read-only query modifier, not a mutation.
Attacks that exploit this kind of access
List all decks. Set include_card_counts=True for per-deck counts. It is categorised as a Read tool in the Codecks MCP Server, which means it retrieves data without modifying state.
Register the Codecks MCP server in PolicyLayer and add a rule for list_decks: 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 Codecks. Nothing to install.
list_decks 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 list_decks 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 list_decks. 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.
list_decks is provided by the Codecks MCP server (rangogamedev/codecks-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 →