Force refresh Tagger tags from docs and write local cache.
AI agents use refresh_tagger_tags to create or update resources in Scryfall MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scryfall MCP Server environment.
This tool writes data to local storage (cache) as a side effect of refreshing tags. It modifies cached state but does not delete data (not Destructive), execute arbitrary code (not Execute), or affect financial systems. The operation is reversible—cache can be refreshed or cleared.
From the tool's definition Tool description states it will 'write local cache', indicating a modification operation. The verb 'refresh' combined with 'write' indicates data is being created or updated locally.
Attacks that exploit this kind of access
Force refresh Tagger tags from docs and write local cache. It is categorised as a Write tool in the Scryfall MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scryfall MCP Server MCP server in PolicyLayer and add a rule for refresh_tagger_tags: 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 Scryfall MCP Server. Nothing to install.
refresh_tagger_tags is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the refresh_tagger_tags 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 refresh_tagger_tags. 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.
refresh_tagger_tags is provided by the Scryfall MCP Server MCP server (latte-chan/scryfall-connector). 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 →