Get time series observations (data points) for a FRED series. Returns the actual data values for an economic indicator over time. Use search_series first to find the series_id, or use well-known IDs like UNRATE, GDP, CPIAUCSL, FEDFUNDS, MORTGAGE30US. For state unemployment, use state abbreviation...
Part of the FRED Economic Data server.
Free to start. No card required.
AI agents call get_series_observations to retrieve information from FRED Economic Data without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_series_observations only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_series_observations": {}
}
}See the full FRED Economic Data policy for all 5 tools.
These attack patterns abuse exactly the kind of access get_series_observations gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get time series observations (data points) for a FRED series. Returns the actual data values for an economic indicator over time. Use search_series first to find the series_id, or use well-known IDs like UNRATE, GDP, CPIAUCSL, FEDFUNDS, MORTGAGE30US. For state unemployment, use state abbreviation + 'UR' (e.g. WAUR for Washington, CAUR for California). Results are sorted most-recent-first. For long series (e.g. daily data since 1954), use start_date/end_date to narrow the window or increase the limit up to 10000. Args: series_id: FRED series identifier (e.g. 'UNRATE', 'GDP', 'CPIAUCSL'). start_date: Optional start date in YYYY-MM-DD format (e.g. '2020-01-01'). end_date: Optional end date in YYYY-MM-DD format (e.g. '2024-12-31'). limit: Maximum observations to return (default 1000, max 10000).. It is categorised as a Read tool in the FRED Economic Data MCP Server, which means it retrieves data without modifying state.
Register the FRED Economic Data MCP server in PolicyLayer and add a rule for get_series_observations: 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 Economic Data. Nothing to install.
get_series_observations 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_series_observations 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_series_observations. 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_series_observations is provided by the FRED Economic Data MCP server (https://mcp.olyport.com/fred/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 FRED Economic Data tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.