AI agents call get_related_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 related tags from FRED economic data. Despite the empty description, the naming convention and server context (read-only data retrieval from a public economic database) strongly indicate a Read operation with no side effects. Even if misused, querying tags poses minimal risk. Confidence is slightly reduced due to missing direct description, but the pattern is clear.
From the tool's definition Tool name is 'get_related_tags' which follows the 'get_' pattern consistent with other data retrieval tools on this server (get_category, get_release, get_release_series).
Attacks that exploit this kind of access
get_related_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_related_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_related_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_related_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_related_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_related_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 →