{
  "markdown": "# FRED MCP Server 📊\n\n[![npm version](https://img.shields.io/npm/v/fred-economic-mcp.svg)](https://www.npmjs.com/package/fred-economic-mcp)\n[![npm downloads](https://img.shields.io/npm/dm/fred-economic-mcp.svg)](https://www.npmjs.com/package/fred-economic-mcp)\n[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n\nU.S. and global economic data for Claude Desktop and any MCP-compatible client, powered by [FRED](https://fred.stlouisfed.org) (Federal Reserve Economic Data). Search and pull from **800,000+ economic time series** — GDP, inflation, unemployment, interest rates, and more — all from natural language.\n\n> **npm package:** [`fred-economic-mcp`](https://www.npmjs.com/package/fred-economic-mcp)  ·  **GitHub repo:** [`danishashko/fred-economic-mcp`](https://github.com/danishashko/fred-economic-mcp).\n\n## 🎯 What You Get\n\n- 🔎 **Search** 800k+ economic series by keyword\n- 📈 **Observations** with built-in transforms (levels, % change, year-over-year) and frequency aggregation (daily → monthly/quarterly/annual)\n- 🧾 **Series metadata** — units, frequency, seasonal adjustment, coverage, notes\n- 🇺🇸 **Economic snapshot** — key U.S. indicators in one call\n- 🗂️ **Category browsing** to discover data by topic\n- 🗓️ **Releases** tracked by FRED\n\nEvery tool returns human-readable **markdown** by default, or structured **JSON** on request (`response_format: \"json\"`). The server is lightweight (Python standard library + `mcp` only), applies FRED's transformations server-side so the AI gets clean numbers, and retries automatically when FRED rate-limits.\n\n## 🔑 Get a Free API Key (required)\n\nFRED requires a free API key. It takes about a minute:\n\n1. Create an account at [fredaccount.stlouisfed.org](https://fredaccount.stlouisfed.org/login/secure/) and request a key at [fredaccount.stlouisfed.org/apikeys](https://fredaccount.stlouisfed.org/apikeys).\n2. Provide it to the server via the `FRED_API_KEY` environment variable (see config below).\n\n## 🚀 Quick Start\n\nAdd this to your Claude Desktop config and restart Claude:\n\n- **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"fred\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"fred-economic-mcp\"],\n      \"env\": {\n        \"FRED_API_KEY\": \"your_free_fred_api_key_here\"\n      }\n    }\n  }\n}\n```\n\nOn first launch the npx wrapper creates an isolated Python environment and installs the dependencies for you (a one-time step that can take a minute). You only need **Python 3.10+** and **Node.js 16+** on your machine.\n\n### Prefer a global install?\n\n```bash\nnpm install -g fred-economic-mcp\n```\n\n```json\n{\n  \"mcpServers\": {\n    \"fred\": {\n      \"command\": \"fred-economic-mcp\",\n      \"env\": { \"FRED_API_KEY\": \"your_free_fred_api_key_here\" }\n    }\n  }\n}\n```\n\n## 🔧 Available Tools\n\n| Tool | What it returns | Parameters |\n|------|-----------------|------------|\n| `search_series` | Series matching a keyword, ranked by popularity (ID, title, units, frequency) | `query`, `limit` |\n| `get_series_observations` | The actual data values, with transforms and frequency aggregation | `series_id`, `observation_start`, `observation_end`, `units`, `frequency`, `sort_order`, `limit` |\n| `get_series_info` | Metadata for a series (units, frequency, seasonal adjustment, coverage, notes) | `series_id` |\n| `get_economic_snapshot` | Latest value of key U.S. indicators in one dashboard | *(none)* |\n| `browse_category` | Child categories and popular series within a FRED category | `category_id` |\n| `get_releases` | Economic data releases FRED tracks | `limit` |\n\nEvery tool also accepts `response_format` (`\"markdown\"`, the default, or `\"json\"`).\n\n**`get_series_observations` transforms (`units`):** `lin` levels · `chg` change · `ch1` change from year ago · `pch` percent change · `pc1` percent change from year ago · `pca` compounded annual rate · `log` natural log.\n\n**Frequency aggregation (`frequency`):** empty (native) · `d` daily · `w` weekly · `m` monthly · `q` quarterly · `a` annual.\n\n### Popular series IDs\n\nYou don't need to memorize IDs — `search_series` finds them — but these come up often:\n\n| Series ID | Indicator |\n|-----------|-----------|\n| `GDPC1` | Real Gross Domestic Product |\n| `UNRATE` | Unemployment Rate |\n| `CPIAUCSL` | Consumer Price Index (CPI) |\n| `PCEPI` | PCE Price Index (the Fed's preferred inflation gauge) |\n| `FEDFUNDS` | Federal Funds Rate |\n| `DGS10` | 10-Year Treasury Yield |\n| `T10Y2Y` | 10-Year minus 2-Year Treasury Spread |\n| `PAYEMS` | Nonfarm Payrolls |\n| `MORTGAGE30US` | 30-Year Fixed Mortgage Rate |\n| `UMCSENT` | Consumer Sentiment (University of Michigan) |\n\n## 💬 Example Prompts\n\nOnce the server is connected, just ask Claude:\n\n- \"How's the U.S. economy doing right now?\"\n- \"What's the current unemployment rate?\"\n- \"Show me year-over-year CPI inflation for the last 12 months.\"\n- \"What's the 10-year Treasury yield, and how has it moved this year?\"\n- \"Find FRED series about consumer credit.\"\n- \"What's the 10Y-2Y yield spread? Is the yield curve inverted?\"\n- \"Compare real GDP growth over the last 8 quarters.\"\n- \"What does the PCEPI series measure, and how often is it updated?\"\n\n### Example output\n\nAsking *\"What's year-over-year CPI inflation for the last few months?\"* runs\n`get_series_observations` with `series_id=CPIAUCSL`, `units=pc1`:\n\n```markdown\n# Consumer Price Index for All Urban Consumers: All Items (CPIAUCSL)\n\n**Units:** Percent change from year ago · **Frequency:** m\n**Total observations:** 940\n\n**Latest:** 3.39 (2026-04-01)\n\n| Date       | Value |\n|------------|-------|\n| 2026-04-01 | 3.39  |\n| 2026-03-01 | 3.29  |\n| 2026-02-01 | 2.43  |\n```\n\n## 🐛 Troubleshooting\n\n**\"No FRED API key configured\"**\nSet `FRED_API_KEY` in your MCP client config (see Quick Start) to a free key from [fredaccount.stlouisfed.org/apikeys](https://fredaccount.stlouisfed.org/apikeys), then restart the client.\n\n**\"Command not found\" / \"Python not found\"**\nMake sure Python 3.10+ and Node.js 16+ are installed and on your PATH. On macOS/Linux, try `python3`.\n\n**\"FRED is rate-limiting requests\"**\nFRED allows 120 requests/minute per key. The server retries automatically; if you still hit it, wait a minute.\n\n**Tools not showing up in Claude**\n1. Confirm the config file is valid JSON (no trailing commas).\n2. Fully quit and reopen Claude Desktop.\n3. Check that `FRED_API_KEY` is set in the server's `env` block.\n\n**\"FRED rejected the request\"**\nThe series ID is probably wrong. Use `search_series` to find the correct ID, or `get_series_info` to confirm a series exists.\n\n**Using a different model or provider (LiteLLM, OpenRouter, NVIDIA NIM, a local model)**\nThis server never talks to a model. Your client starts it as a local process and\nspeaks JSON-RPC over stdin/stdout, so changing `ANTHROPIC_BASE_URL` or swapping the\nmodel behind your client has no effect on it. If tools stop firing after a switch\nlike that, check two things: the model has to support function calling, and a proxy\nconfigured to drop unsupported parameters can silently strip your tool definitions,\nwhich produces no error at all. Run `/mcp` in your client (or `claude mcp list`) to\nconfirm the server is connected before suspecting the server.\n\n## 🛠️ Manual Installation (Alternative)\n\nIf you would rather run the Python file directly instead of via npx:\n\n**1. Download the server and install the dependency**\n\nSave `fred_mcp.py` somewhere on your machine, then:\n\n```bash\npip install mcp\n```\n\n(or `pip3` on macOS/Linux)\n\n**2. Point Claude Desktop at it**\n\n```json\n{\n  \"mcpServers\": {\n    \"fred\": {\n      \"command\": \"python3\",\n      \"args\": [\"/absolute/path/to/fred_mcp.py\"],\n      \"env\": { \"FRED_API_KEY\": \"your_key_here\" }\n    }\n  }\n}\n```\n\nOn Windows use `\"command\": \"python\"` and a path like `\"C:\\\\path\\\\to\\\\fred_mcp.py\"` (double backslashes or forward slashes).\n\n**3. Restart Claude Desktop.**\n\n## 🔒 Privacy & Rate Limits\n\n- Uses the official [FRED API](https://fred.stlouisfed.org/docs/api/fred/) with your own free API key.\n- Requests go straight from your machine to FRED. Nothing is stored or proxied.\n- FRED rate-limits **120 requests/minute per key**; the server retries with backoff on `429`.\n- Intended for personal, educational, and research use.\n\n## 📝 Notes\n\n- Series IDs are case-insensitive here (they're upper-cased for you), e.g. `unrate` works.\n- FRED marks missing observations with `.`; those are shown as `N/A`.\n- The `units` transforms (e.g. `pc1` for year-over-year %) are computed by FRED, so the values are authoritative — no client-side math.\n- Data coverage and frequency vary by series; use `get_series_info` to check before pulling a range.\n\n## 📋 Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for the full version history.\n\n## 📚 Resources\n\n- [Model Context Protocol](https://modelcontextprotocol.io/)\n- [FRED API documentation](https://fred.stlouisfed.org/docs/api/fred/)\n- [Get a FRED API key](https://fredaccount.stlouisfed.org/apikeys)\n\n## ⚖️ Legal Disclaimer\n\nThis tool uses the FRED® API but is not endorsed or certified by the Federal Reserve Bank of St. Louis. FRED® is a registered trademark of the Federal Reserve Bank of St. Louis. Use of the FRED API is subject to its [Terms of Use](https://fred.stlouisfed.org/docs/api/terms_of_use.html).\n\n## 👤 Author\n\n**Daniel Shashko**\n- GitHub: [@danishashko](https://github.com/danishashko)\n- LinkedIn: [daniel-shashko](https://linkedin.com/in/daniel-shashko)\n- npm: [danielshashko](https://www.npmjs.com/~danielshashko)\n\n## 📄 License\n\nMIT © Daniel Shashko\n",
  "bytes": 9720,
  "sha": "ac4c32da759a0e144a6689cf68be2baffbf0dc3f1c51feb3a7104b84919da3a6",
  "repo_slug": "danishashko/fred-economic-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_danishashko_fred_economic_mcp_f3f9eedc/readme"
}