AI agents call tool_fetch_moxfield_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.
Fetching deck data from Moxfield is a read-only operation with no side effects—it queries and retrieves existing deck information. This aligns with the Read category pattern (search, list, get, fetch). Confidence is slightly reduced from maximum because the tool description is empty, leaving some ambiguity about exact implementation details, but the name and context strongly suggest a retrieval operation.
From the tool's definition Tool name 'fetch_moxfield_deck' uses the 'fetch' verb, indicating data retrieval. The sibling tool 'mtg-moxfield-fetch' on the same server appears to perform similar fetch operations.
Attacks that exploit this kind of access
tool_fetch_moxfield_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 tool_fetch_moxfield_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.
tool_fetch_moxfield_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 tool_fetch_moxfield_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 tool_fetch_moxfield_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.
tool_fetch_moxfield_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 →