Get Federal Reserve speeches by document type (speech, testimony, or prepared_remarks).
AI agents call get_speeches_by_type to retrieve information from Fed Speech MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing Federal Reserve speeches and testimonies by type classification. It queries a data collection without side effects, making it a straightforward Read operation. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an agent could only retrieve more speeches than intended, which has negligible security impact.
From the tool's definition Tool description states 'Get Federal Reserve speeches by document type' — a retrieval operation with no modification, deletion, or execution capability. The server is explicitly designed for retrieval, parsing, and analysis of public Federal Reserve data.
Attacks that exploit this kind of access
Get Federal Reserve speeches by document type (speech, testimony, or prepared_remarks). It is categorised as a Read tool in the Fed Speech MCP MCP Server, which means it retrieves data without modifying state.
Register the Fed Speech MCP server in PolicyLayer and add a rule for get_speeches_by_type: 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 Fed Speech MCP. Nothing to install.
get_speeches_by_type 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_speeches_by_type 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_speeches_by_type. 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_speeches_by_type is provided by the Fed Speech MCP server (zsun4work/fed-speech-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 →