Federal Reserve Economic Data (FRED)
Provides access to over 800,000 economic time series from the Federal Reserve, allowing users to browse, search, and retrieve data for indicators like GDP and unemployment. It supports custom date ranges and data transformations such as percentage ch
What is Federal Reserve Economic Data (FRED)?
Federal Reserve Economic Data (FRED) is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides access to over 800,000 economic time series from the federal reserve, allowing users to browse, search, and retrieve data for indicators like gdp and unemployment. it supports custom date ran...
Provides access to over 800,000 economic time series from the Federal Reserve, allowing users to browse, search, and retrieve data for indicators like GDP and unemployment. It supports custom date ranges and data transformations such as percentage ch
This server falls under the Finance & Fintech and Analytics categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- RRPONTSYD
Use Cases
Maintainer
Works with
Installation
NPM
npx -y fred-mcp-serverManual Installation
npx -y fred-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Federal Reserve Economic Data (FRED)
The FRED MCP Server provides AI assistants with universal access to all 800,000+ economic time series published by the Federal Reserve Bank of St. Louis through the FRED API, including indicators such as GDP, unemployment rate (UNRATE), CPI, interest rates, and thousands more. It exposes three tools — fred_browse for navigating categories and releases, fred_search for keyword and tag-based discovery, and fred_get_series for retrieving actual time series data with support for custom date ranges and data transformations including percentage change, year-over-year change, and log transformation. A FRED API key is required and can be obtained free of charge from the FRED website.
Prerequisites
- Node.js 18 or later (for running via npx or from source)
- A free FRED API key from https://fred.stlouisfed.org/docs/api/api_key.html
- An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code CLI
- pnpm (for building from source)
Obtain a FRED API key
Register for a free API key at the FRED website. The key is required for all API calls — without it the server will fail to retrieve any data.
# Visit: https://fred.stlouisfed.org/docs/api/api_key.html
# Create an account and request a free API keyRun the server with npx
The server can be run directly via npx without any installation. Pass your FRED API key as an environment variable.
FRED_API_KEY=your_key_here npx -y fred-mcp-serverConfigure your MCP client
Add the FRED MCP server to your client configuration with your API key set as an environment variable. This is the recommended approach for persistent use.
Test data retrieval
Verify the server is working by asking your AI assistant to retrieve a well-known series such as GDP or UNRATE. The server should return observation data with dates and values.
Optional: run via Docker
For containerized deployments, use the Docker image which bundles the server without requiring Node.js on the host.
docker run -i --rm -e FRED_API_KEY=your_key_here stefanoamorelli/fred-mcp-server:latestFederal Reserve Economic Data (FRED) Examples
Client configuration
Claude Desktop configuration for the FRED MCP server using npx with the API key as an environment variable.
{
"mcpServers": {
"FRED MCP Server": {
"command": "npx",
"args": ["-y", "fred-mcp-server"],
"env": {
"FRED_API_KEY": "your_fred_api_key_here"
}
}
}
}Prompts to try
Sample prompts for retrieving and analyzing Federal Reserve economic data through the MCP server.
- "Get the US GDP data for the last 10 years and show it as percent change"
- "What is the current US unemployment rate? Retrieve the UNRATE series"
- "Search FRED for economic series related to inflation and CPI"
- "Retrieve the federal funds rate (FEDFUNDS) from 2020 to 2024"
- "Browse the FRED categories to find money supply data"
- "Get monthly CPI data (CPIAUCSL) and calculate the year-over-year percent change"Troubleshooting Federal Reserve Economic Data (FRED)
All FRED API calls return 403 or 'Bad API key' errors
Verify that FRED_API_KEY is correctly set in your MCP client configuration and that the key is active. Keys are tied to an email address — log into fred.stlouisfed.org to confirm your key is valid and has not been revoked.
fred_get_series returns no observations for a series
Check that the series ID is correct — FRED series IDs are case-sensitive (e.g., GDP, UNRATE, CPIAUCSL). Use fred_search to find the exact series ID before retrieving data. Also verify the date range falls within the series' available data window.
The server starts but npx times out downloading the package
Run npm install -g fred-mcp-server once to cache the package globally, then use fred-mcp-server as the command in your client config instead of npx. Alternatively, clone and build from source following the repository instructions.
Frequently Asked Questions about Federal Reserve Economic Data (FRED)
What is Federal Reserve Economic Data (FRED)?
Federal Reserve Economic Data (FRED) is a Model Context Protocol (MCP) server that provides access to over 800,000 economic time series from the federal reserve, allowing users to browse, search, and retrieve data for indicators like gdp and unemployment. it supports custom date ranges and data transformations such as percentage ch It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Federal Reserve Economic Data (FRED)?
Install via npm with the command: npx -y fred-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Federal Reserve Economic Data (FRED)?
Federal Reserve Economic Data (FRED) works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Federal Reserve Economic Data (FRED) free to use?
Yes, Federal Reserve Economic Data (FRED) is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.
Federal Reserve Economic Data (FRED) Alternatives — Similar Finance & Fintech Servers
Looking for alternatives to Federal Reserve Economic Data (FRED)? Here are other popular finance & fintech servers you can use with Claude, Cursor, and VS Code.
ValueCell
★ 10.7kValueCell is a community-driven, multi-agent platform for financial applications.
Vibe Trading
★ 8.1k'Vibe-Trading: Your Personal Trading Agent'
Quantdinger
★ 6.2kAI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
TradingView
★ 2.8kReal-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick patterns + native Claude Desktop integration. Multi-exchange (Binance, KuCoin, Bybit+). Open-source AI trading infrastructure.
Financial Datasets
★ 2.1kProvides access to comprehensive financial data including income statements, balance sheets, cash flow statements, stock prices, company news, SEC filings, and cryptocurrency information with built-in financial ratio analysis.
Stripe
★ 1.6kThe Stripe Model Context Protocol server allows you to integrate with Stripe APIs through function calling. This protocol supports various tools to interact with different Stripe services.
Browse More Finance & Fintech MCP Servers
Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Federal Reserve Economic Data (FRED) in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Federal Reserve Economic Data (FRED)?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.