AI agents call get_categories to retrieve information from Mcp Fred without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays category structure/metadata from the Federal Reserve's public economic database. Browsing a category tree is a non-destructive query operation with no side effects. The blast radius of misuse is minimal—worst case, an agent browses unexpected categories, but no data is modified, deleted, or financial transactions occur. This is a straightforward Read classification.
From the tool's definition Tool name 'get_categories' and description 'Browse the FRED category tree' indicate a read-only retrieval operation that queries hierarchical category metadata from the FRED API.
Attacks that exploit this kind of access
Browse the FRED category tree. It is categorised as a Read tool in the Mcp Fred MCP Server, which means it retrieves data without modifying state.
Register the Mcp Fred MCP server in PolicyLayer and add a rule for get_categories: 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 Mcp Fred. Nothing to install.
get_categories 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_categories 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_categories. 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_categories is provided by the Mcp Fred MCP server (petrefiedthunder/mcp-fred). 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 →