AI agents call tool_search_combos 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.
This tool queries an external API (Commander Spellbook) to fetch combo interaction data. It retrieves information without side effects, making it a Read operation. The blast radius of misuse is minimal: returning irrelevant or verbose combo data poses no security or operational risk.
From the tool's definition Tool name includes 'search' and description states it 'Search for Commander combos involving a specific card' — a retrieval operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Search for Commander combos involving a specific card using the Commander Spellbook API. 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 tool_search_combos: 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.
tool_search_combos 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 tool_search_combos 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 tool_search_combos. 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.
tool_search_combos 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 →