Connect FRED (Federal Reserve Economic Data) to Copilot Studio
Query FRED (Federal Reserve Economic Data) directly from Copilot Studio. Arlet links the two through one MCP connection and takes care of API keys.
This server connects your AI client to FRED, the Federal Reserve Bank of St. Louis' economic data service, which aggregates hundreds of thousands of time series from US federal statistical agencies and international organizations into one consistent API.
Key features:
- search_series: find the right series by keyword, returning each candidate's id, title, units, frequency and seasonal-adjustment status. Picking the correct series is usually the hard part of economic analysis, so this metadata comes back before you fetch any data.
- get_series_observations: fetch the observations for a series id, with a date range, frequency aggregation, and unit transformations computed upstream (change, percent change, percent change from a year ago, compounded annual rate, log). Missing observations are normalized to null instead of FRED's '.' sentinel.
- list_release_dates: look up the publication calendar - when a statistic such as CPI or the employment situation was or will be released.
Because FRED already harmonizes vintages, units and frequencies across source agencies, it is usually a better first stop than each agency's own API when you need a US macro series.
Using the API requires a free API key issued from your FRED account. Set it as FRED_API_KEY in your Arlet environment variables. FRED's terms ask that you attribute the source; every tool response includes the attribution text.
How to connect FRED (Federal Reserve Economic Data) to Copilot Studio
- 1
In the Arlet dashboard, open Data tools, find FRED (Federal Reserve Economic Data), set the API key issued by FRED (Federal Reserve Economic Data) and switch it on.
- 2
Sign in to Copilot Studio with your work account, create a new agent (or open an existing one), and in the Build tab choose Tools → + → Add → Model Context Protocol (MCP) in the right panel.
- 3
In the Add MCP server form, enter "Arlet" as the Server name, https://mcp.arlet.dev/mcp/ as the Server URL, choose OAuth 2.0 for Authentication and "Dynamic (detected)" for Configuration type, then click Add. No Client ID / Secret is needed.
- 4
On the Select a connection screen, choose Create new connection → Create, then sign in with Google on the Arlet authorization screen and click Allow. Click Add to attach the tool to the agent, then Publish to use it from Microsoft 365 Copilot.
Requires a Microsoft work account and a Copilot Studio license (or trial). MCP is available only for agents using generative orchestration and not in Copilot Studio in Teams.