Server data from the Official MCP Registry
FRED economic data: GDP, inflation, unemployment, rates, and 800k+ Federal Reserve time series.
FRED economic data: GDP, inflation, unemployment, rates, and 800k+ Federal Reserve time series.
This is a well-structured MCP server for accessing FRED economic data. Authentication is properly required via environment variable, code quality is solid with good error handling and input validation, and permissions align with the server's stated purpose (read-only API access to FRED). Minor observations: the server properly avoids logging sensitive data, handles rate-limiting gracefully, and uses standard library + minimal dependencies. No security vulnerabilities detected. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
6 files analyzed ยท 7 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: FRED_API_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-danishashko-fred-economic-mcp": {
"env": {
"FRED_API_KEY": "your-fred-api-key-here"
},
"args": [
"-y",
"fred-economic-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
U.S. and global economic data for Claude Desktop and any MCP-compatible client, powered by FRED (Federal Reserve Economic Data). Search and pull from 800,000+ economic time series โ GDP, inflation, unemployment, interest rates, and more โ all from natural language.
npm package:
fred-economic-mcpย ยทย GitHub repo:danishashko/fred-economic-mcp.
Every 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.
FRED requires a free API key. It takes about a minute:
FRED_API_KEY environment variable (see config below).Add this to your Claude Desktop config and restart Claude:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"fred": {
"command": "npx",
"args": ["-y", "fred-economic-mcp"],
"env": {
"FRED_API_KEY": "your_free_fred_api_key_here"
}
}
}
}
On 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.
npm install -g fred-economic-mcp
{
"mcpServers": {
"fred": {
"command": "fred-economic-mcp",
"env": { "FRED_API_KEY": "your_free_fred_api_key_here" }
}
}
}
| Tool | What it returns | Parameters |
|---|---|---|
search_series | Series matching a keyword, ranked by popularity (ID, title, units, frequency) | query, limit |
get_series_observations | The actual data values, with transforms and frequency aggregation | series_id, observation_start, observation_end, units, frequency, sort_order, limit |
get_series_info | Metadata for a series (units, frequency, seasonal adjustment, coverage, notes) | series_id |
get_economic_snapshot | Latest value of key U.S. indicators in one dashboard | (none) |
browse_category | Child categories and popular series within a FRED category | category_id |
get_releases | Economic data releases FRED tracks | limit |
Every tool also accepts response_format ("markdown", the default, or "json").
get_series_observations transforms (units): lin levels ยท chg change ยท ch1 change from year ago ยท pch percent change ยท pc1 percent change from year ago ยท pca compounded annual rate ยท log natural log.
Frequency aggregation (frequency): empty (native) ยท d daily ยท w weekly ยท m monthly ยท q quarterly ยท a annual.
You don't need to memorize IDs โ search_series finds them โ but these come up often:
| Series ID | Indicator |
|---|---|
GDPC1 | Real Gross Domestic Product |
UNRATE | Unemployment Rate |
CPIAUCSL | Consumer Price Index (CPI) |
PCEPI | PCE Price Index (the Fed's preferred inflation gauge) |
FEDFUNDS | Federal Funds Rate |
DGS10 | 10-Year Treasury Yield |
T10Y2Y | 10-Year minus 2-Year Treasury Spread |
PAYEMS | Nonfarm Payrolls |
MORTGAGE30US | 30-Year Fixed Mortgage Rate |
UMCSENT | Consumer Sentiment (University of Michigan) |
Once the server is connected, just ask Claude:
Asking "What's year-over-year CPI inflation for the last few months?" runs
get_series_observations with series_id=CPIAUCSL, units=pc1:
# Consumer Price Index for All Urban Consumers: All Items (CPIAUCSL)
**Units:** Percent change from year ago ยท **Frequency:** m
**Total observations:** 940
**Latest:** 3.39 (2026-04-01)
| Date | Value |
|------------|-------|
| 2026-04-01 | 3.39 |
| 2026-03-01 | 3.29 |
| 2026-02-01 | 2.43 |
"No FRED API key configured"
Set FRED_API_KEY in your MCP client config (see Quick Start) to a free key from fredaccount.stlouisfed.org/apikeys, then restart the client.
"Command not found" / "Python not found"
Make sure Python 3.10+ and Node.js 16+ are installed and on your PATH. On macOS/Linux, try python3.
"FRED is rate-limiting requests" FRED allows 120 requests/minute per key. The server retries automatically; if you still hit it, wait a minute.
Tools not showing up in Claude
FRED_API_KEY is set in the server's env block."FRED rejected the request"
The series ID is probably wrong. Use search_series to find the correct ID, or get_series_info to confirm a series exists.
If you would rather run the Python file directly instead of via npx:
1. Download the server and install the dependency
Save fred_mcp.py somewhere on your machine, then:
pip install mcp
(or pip3 on macOS/Linux)
2. Point Claude Desktop at it
{
"mcpServers": {
"fred": {
"command": "python3",
"args": ["/absolute/path/to/fred_mcp.py"],
"env": { "FRED_API_KEY": "your_key_here" }
}
}
}
On Windows use "command": "python" and a path like "C:\\path\\to\\fred_mcp.py" (double backslashes or forward slashes).
3. Restart Claude Desktop.
429.unrate works..; those are shown as N/A.units transforms (e.g. pc1 for year-over-year %) are computed by FRED, so the values are authoritative โ no client-side math.get_series_info to check before pulling a range.See CHANGELOG.md for the full version history.
This tool uses the FREDยฎ API but is not endorsed or certified by the Federal Reserve Bank of St. Louis. FREDยฎ is a registered trademark of the Federal Reserve Bank of St. Louis. Use of the FRED API is subject to its Terms of Use.
Daniel Shashko
MIT ยฉ Daniel Shashko
Be the first to review this server!
by Modelcontextprotocol ยท Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno ยท Developer Tools
Toleno Network MCP Server โ Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace ยท Developer Tools
Create, build, and publish Python MCP servers to PyPI โ conversationally.