get_fred_series_observationsLABSCO SUMMARY
Economic series, current, by ID.
It does one thing: return the observations of a named FRED series. That is what most questions about inflation, unemployment or rates actually need, and it is the part a model cannot answer from memory.
What it is
A reader for the Federal Reserve Bank of St. Louis's FRED data, built on the series_observations endpoint. Give it a series ID and the time series comes back, with the API's own parameters for date range, ordering and units available on the same call.
What you get
- Any FRED series fetched by its ID, as dated observations
- The API's own filters on the same call — date range, sort order, unit transformations
- Figures read from the source rather than from a model's memory of them
Requirements
A FRED API key from the St. Louis Fed, set in a .env file, and uv or pip to run the server.
Setup effort
Build from source — git clone https://github.com/Jaldekoa/mcp-fredapi.git
USE CASES
01
Answering a question about inflation with current numbers
The CPI series comes back as dated observations, so the answer carries the release it came from instead of a remembered figure.
02
Comparing two indicators over the same window
Ask for each series with the same date range and sort order, and the two line up without any reshaping.
03
Charting a series without downloading a CSV
Observations arrive in the session ready to plot or summarize, which removes the download-and-clean step entirely.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
FRED_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install uv
git clone https://github.com/Jaldekoa/mcp-fredapi.git
cd mcp-fredapiMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"mcp-fredapi": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_FREDAPI>",
"run",
"--with",
"mcp",
"--with",
"httpx",
"mcp",
"run",
"server.py"
]
}
}
}The configuration on this page does not set FRED_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.
