AI agents call mtg-commander-deck to retrieve information from MTG-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description reducing confidence, the tool name and ecosystem of sibling tools (all read-only: fetch, get, search, recommend) strongly suggest this retrieves Commander deck information without side effects. The most likely function is deck lookup, recommendation, or export—all Read operations. No evidence of writes, destructive actions, or external effects.
From the tool's definition Tool name 'mtg-commander-deck' with no description; sibling tools like 'mtg-commander-recommend', 'mtg-export-format', and 'mtg-moxfield-fetch' suggest this retrieves or formats Commander deck data rather than modifying it.
Attacks that exploit this kind of access
mtg-commander-deck. It is categorised as a Read tool in the MTG-MCP MCP Server, which means it retrieves data without modifying state.
Register the MTG- MCP server in PolicyLayer and add a rule for mtg-commander-deck: 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 MTG-MCP. Nothing to install.
mtg-commander-deck 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 mtg-commander-deck 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 mtg-commander-deck. 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.
mtg-commander-deck is provided by the MTG- MCP server (wtfregia/mtg-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 →