AI agents call get_category_children 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 hierarchical category data from FRED without modifying anything. It is a read-only query operation consistent with the broader data retrieval purpose of the server. Empty description slightly lowers confidence from 0.99 to 0.95, but the naming convention and context make the classification clear.
From the tool's definition Tool name 'get_category_children' combined with server purpose of 'querying and retrieving Federal Reserve Economic Data' and sibling tools all using 'get_' prefix for data retrieval operations (get_category, get_release, get_release_series, etc.).
Attacks that exploit this kind of access
get_category_children. 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_children: 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_children 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_children 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_children. 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_children 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 →