AI agents call get_category_tags to retrieve information from Fred without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tags associated with a FRED category. It performs a query operation with no side effects, no state modifications, no execution of external code, and no financial impact. The 'get_' prefix and context of a read-only data API confirm this is a Read operation. Severity is low because retrieving public economic metadata poses minimal risk even if misused.
From the tool's definition Tool name 'get_category_tags' combined with sibling tools pattern (all prefixed with 'get_') and server purpose of 'querying and retrieving Federal Reserve Economic Data'.
Attacks that exploit this kind of access
get_category_tags. It is categorised as a Read tool in the Fred MCP Server, which means it retrieves data without modifying state.
Register the Fred MCP server in PolicyLayer and add a rule for get_category_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 Fred. Nothing to install.
get_category_tags 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 get_category_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 get_category_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.
get_category_tags is provided by the Fred MCP server (zachspar/fred-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 →