AI agents call fred_get_canonical_indicators to retrieve information from Self without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve reference data about canonical economic indicators from FRED—a standard read operation. It retrieves or queries data with no side effects. Even though the description is empty, the context of the server (economic data queries) and naming pattern align with safe, read-only access.
From the tool's definition Tool name 'fred_get_canonical_indicators' and sibling tools like 'fred_get_observations', 'fred_get_series', 'fred_get_latest_observation', 'fred_get_macro_snapshot' all follow read-only query patterns typical of FRED (Federal Reserve Economic Data) API…
Attacks that exploit this kind of access
fred_get_canonical_indicators. It is categorised as a Read tool in the Self MCP Server, which means it retrieves data without modifying state.
Register the Self MCP server in PolicyLayer and add a rule for fred_get_canonical_indicators: 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 Self. Nothing to install.
fred_get_canonical_indicators 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 fred_get_canonical_indicators 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 fred_get_canonical_indicators. 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.
fred_get_canonical_indicators is provided by the Self MCP server (ryanwang945/self-mcp-server). 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 →