[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [FRED historical observations](https://spiral.ai/integrations/gemini-cli/fred-historical-observations)

# How to Use FRED historical observations in Gemini CLI

Returns dated values for an economic series. Use it to compare periods, calculate changes, or examine a trend after checking the series definition and available history.

|  |  |
| --- | --- |
| Model | FRED historical observations |
| Available through | Alexandria |
| Category | Finance |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FRED historical observations in Gemini CLI

- Use FRED historical observations to compare UNRATE during 2019 and 2020. Report the monthly values and the largest month-to-month percentage-point increase.
- Use FRED historical observations to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from FRED historical observations and tell me what changed since last week.
- Check FRED historical observations and summarize what you find in three bullet points.
- Pull the newest data from FRED historical observations and give me the result as a table.

## How to set up FRED historical observations in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run FRED historical observations**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "fred-stlouisfed-org/economic-data/series_observations",
    "input": {
      "series_id": "<series_id>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds FRED historical observations on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## FRED historical observations tools and prices

- [FRED (Federal Reserve Economic Data) · Series observations](https://spiral.ai/tools/alexandria/fred-stlouisfed-org/economic-data/series_observations) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| limit | 1 to 10000 | 1000 | Observations per page. |
| units | lin, chg, ch1, pch, pc1, pca, cch, cca, log | lin | FRED transformation code: lin levels, chg change, ch1 change from year ago, pch percent change, pc1 percent change from year ago, pca compounded annual rate of change, cch continuously compounded rate of change, cca continuously compounded annual rate of change, log natural log. |
| offset | 0 to … | 0 | Zero-based index of the first observation to return, in `sort_order`; pass `next_offset` from the previous page. |
| frequency | d, w, bw, m, q, sa, a | — | Aggregate to a lower frequency (FRED API codes: d daily, w weekly, bw biweekly, m monthly, q quarterly, sa semiannual, a annual). Omit for the native frequency. |
| sort_order | asc, desc | asc | Date order of the observations. |
| observation_end |  | — | Last observation date (inclusive), YYYY-MM-DD. Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. |

## What can you do with FRED historical observations in Gemini CLI?

Check the economic definitions behind an analysis before interpreting its results. A coding agent can inspect FRED series, reporting periods, and publishing agencies to explain whether the selected indicators answer the research question.

### Manufacturing conditions briefing

Find production and employment indicators through topics, tags, publications, or publishing agencies. Compare their histories with steel producer price indexes, keeping each measure's units and reporting frequency visible.

### Steel benchmark selection

Explore steel measures through keyword searches, product topics, tags, and the Producer Price Index release. Compare definitions and available histories before choosing a benchmark for cold-rolled sheet or another specific product.

### Procurement research report

Trace steel index results to the publishing agency and statistical release. Explain the selected measure's definition and historical changes alongside its source citation.

### Classroom comparison of economic measures

Find unemployment, output, and steel price indicators by topic, keywords, or tags. Use their definitions and observations to explain how a percentage, an output measure, and a producer price index answer different questions.

### Economic reporting coverage audit

Check whether a proposed manufacturing brief has suitable indicators and sufficient history. Explore candidate series through FRED's discovery routes, inspect their definitions and observation boundaries, and identify steel indexes whose data stop before the report period.

### Steel trend explanation

Compare a steel index summary with its historical observations and series definition. Explain the period covered and the change in the index without treating its level as a supplier quote.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## FRED historical observations in other agents

- [Amp](https://spiral.ai/integrations/amp/fred-historical-observations)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/fred-historical-observations)
- [Claude](https://spiral.ai/integrations/claude-desktop/fred-historical-observations)
- [Claude Code](https://spiral.ai/integrations/claude-code/fred-historical-observations)
- [Cline](https://spiral.ai/integrations/cline/fred-historical-observations)
- [Codex](https://spiral.ai/integrations/codex/fred-historical-observations)
- [Cursor](https://spiral.ai/integrations/cursor/fred-historical-observations)
- [Devin](https://spiral.ai/integrations/devin/fred-historical-observations)
- [dots](https://spiral.ai/integrations/dots/fred-historical-observations)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/fred-historical-observations)
- [Gemini](https://spiral.ai/integrations/gemini/fred-historical-observations)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/fred-historical-observations)
- [goose](https://spiral.ai/integrations/goose/fred-historical-observations)
- [Grok](https://spiral.ai/integrations/grok/fred-historical-observations)
- [Grok Build](https://spiral.ai/integrations/grok-build/fred-historical-observations)
- [Hermes](https://spiral.ai/integrations/hermes/fred-historical-observations)
- [Instinct](https://spiral.ai/integrations/instinct/fred-historical-observations)
- [Manus](https://spiral.ai/integrations/manus/fred-historical-observations)
- [Muse](https://spiral.ai/integrations/muse/fred-historical-observations)
- [Muse Code](https://spiral.ai/integrations/muse-code/fred-historical-observations)
- [n8n](https://spiral.ai/integrations/n8n/fred-historical-observations)
- [Notion](https://spiral.ai/integrations/notion/fred-historical-observations)
- [OpenClaw](https://spiral.ai/integrations/openclaw/fred-historical-observations)
- [opencode](https://spiral.ai/integrations/opencode/fred-historical-observations)
- [Perplexity](https://spiral.ai/integrations/perplexity/fred-historical-observations)
- [Raycast](https://spiral.ai/integrations/raycast/fred-historical-observations)
- [VS Code](https://spiral.ai/integrations/vscode/fred-historical-observations)
- [Windsurf](https://spiral.ai/integrations/windsurf/fred-historical-observations)
- [Zapier](https://spiral.ai/integrations/zapier/fred-historical-observations)

## More Gemini CLI guides

- [FRED economic series search](https://spiral.ai/integrations/gemini-cli/fred-economic-series-search)
- [FRED publication date history](https://spiral.ai/integrations/gemini-cli/fred-publication-date-history)
- [FRED economic series by tag](https://spiral.ai/integrations/gemini-cli/fred-economic-series-by-tag)
- [FRED publisher details](https://spiral.ai/integrations/gemini-cli/fred-publisher-details)
- [FRED economic releases](https://spiral.ai/integrations/gemini-cli/fred-economic-releases)
- [FRED publisher directory](https://spiral.ai/integrations/gemini-cli/fred-publisher-directory)

## Questions about FRED historical observations in Gemini CLI

**Can Gemini CLI use FRED historical observations?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run FRED historical observations like any built-in tool.

**How much does FRED historical observations cost in Gemini CLI?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an Alexandria account to use FRED historical observations in Gemini CLI?**

No. Spiral runs FRED historical observations on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up FRED historical observations in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while FRED historical observations runs?**

FRED historical observations runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**Does FRED cover only the United States?**

FRED includes international, national, and regional economic series. Its database draws from more than 100 public and proprietary sources.

**How fresh is FRED's data?**

FRED updates its database daily, but individual indicators follow their own reporting frequencies. For example, UNRATE is monthly, while GDPC1 is quarterly.

**Can previously published values change?**

Yes. FRED displays the latest version of a series, and replaced versions are archived in ALFRED, so today's historical values can differ from earlier publications.

**Does every series continue through the latest reporting period?**

No. For example, the hot-rolled steel sheet and strip index WPU10170301 has a final observation in February 2022, even though its page displays a future release date.

**How does FRED check data accuracy?**

When a release is added or updated, FRED compares it with data already published by the same source. Its checks also flag unexpected values and verify reported frequency and date formats.

