fred
Open-source FRED MCP Server (Federal Reserve Economic Data)
claude mcp add --transport stdio stefanoamorelli-fred-mcp-server node <PATH_TO_YOUR_REPO>/fred-mcp-server/build/index.js \ --env FRED_API_KEY="<YOUR_API_KEY>"
How to use
This MCP server provides universal access to the Federal Reserve Economic Data (FRED) time series through three dedicated tools: fred_browse, fred_search, and fred_get_series. You can browse the complete catalog of series by categories, releases, or sources, search for indicators by keywords or tags, and retrieve data for any FRED series with optional transformations and date filters. When using Streamable HTTP transport, you interact with the server via HTTP requests to the /mcp endpoint, sending JSON-RPC style payloads to initialize a session and then call the available tools. The server exposes the three tools in a consistent interface and supports common paging and filtering options for large results sets.
How to install
Prerequisites:
- Node.js (and npm/pnpm as needed) installed on your system
- Access to a FRED API key
Manual installation steps:
- Clone the repository:
git clone https://github.com/stefanoamorelli/fred-mcp-server.git
cd fred-mcp-server
- Install dependencies (pnpm is used in the project; you can adapt to npm/yarn as needed):
pnpm install
- Build the project:
pnpm build
- Obtain a FRED API key from https://fred.stlouisfed.org/docs/api/api_key.html and create a config file or environment setup to provide FRED_API_KEY.
- Run with Node (example):
node build/index.js
- If you prefer Docker, see the Docker usage instructions in the README to run the server with a key environment variable.
Additional notes
Tips and common issues:
- You must provide a valid FRED_API_KEY via environment variable FRED_API_KEY when starting the server.
- If using Docker, replace <your-key-here> with your actual API key and ensure the container has network access.
- When using Streamable HTTP transport, you can customize the port with the PORT environment variable (default 3000).
- The MCP tools support common parameters such as limit, offset, order_by, sort_order, and various series-specific filters. Review the README's tool sections for exact parameters.
- If you encounter rate limits or API errors from FRED, consider caching results or implementing client-side retries with backoff.
- For CLI/SDK usage, the server follows standard MCP JSON-RPC structure: initialize, then call tools/list or specific tool methods with appropriate params.
Related MCP Servers
FinanceMCP
这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型(如Claude)提供全面的实时金融数据访问能力,支持股票、基金、债券、宏观经济指标、稳定币、虚拟货币等多维度金融数据分析。其中也包含了金融数据查询、财经新闻查询、国家统计局数据查询等
sec-edgar
A SEC EDGAR MCP (Model Context Protocol) Server
git
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management, and more, via the MCP standard. STDIO & HTTP.
mcp-streamable-http
Example implementation of MCP Streamable HTTP client/server in Python and TypeScript.
mcp
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.
nasdaq-data-link
A Nasdaq Data Link MCP (Model Context Protocol) Server