AI agents call mtg-combos-search 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.
Search tools are inherently Read operations that query and retrieve data. The naming convention and server context strongly indicate this retrieves Magic: The Gathering combo information for informational purposes only, with no capability to modify, execute, or delete data.
From the tool's definition Tool name 'mtg-combos-search' indicates a search operation. The empty description prevents direct confirmation, but contextual analysis of sibling tools (all read-only: -fetch, -get, -recommend, -search patterns) and the MTG server's stated purpose of…
Attacks that exploit this kind of access
mtg-combos-search. 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-combos-search: 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-combos-search 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-combos-search 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-combos-search. 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-combos-search 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 →