AI agents call search_series_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.
The tool searches for series tags in a read-only Federal Reserve Economic Data dataset. No mutation, deletion, or code execution is indicated. The operation has minimal blast radius—at worst it returns unexpected data subsets. Although the description is empty, the naming convention and server context strongly indicate a retrieval/query function consistent with the Read category.
From the tool's definition Tool name 'search_series_tags' combined with context that the FRED-MCP server 'enables querying and retrieving Federal Reserve Economic Data' indicates a search/query operation.
Attacks that exploit this kind of access
search_series_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 search_series_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.
search_series_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 search_series_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 search_series_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.
search_series_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 →