[Integrations](https://spiral.ai/integrations) › [Claude](https://spiral.ai/integrations/claude-desktop) › [Census dataset search](https://spiral.ai/integrations/claude-desktop/census-dataset-search)

# How to Use Census dataset search in Claude

Returns matching Census datasets with their reference years and metadata links. Use it to find the right statistical program before choosing measures or requesting observations.

|  |  |
| --- | --- |
| Model | Census dataset search |
| Available through | Alexandria |
| Category | Public Records |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Census dataset search in Claude

- Use Census dataset search to find 2024 American Community Survey five-year housing datasets suitable for comparing census tracts in Wake County, North Carolina.
- Use Census dataset search to look this up and give me the result as a table.
- Pull the latest numbers from Census dataset search and tell me what changed since last week.
- Check Census dataset search and summarize what you find in three bullet points.
- Pull the newest data from Census dataset search and give me the result as a table.

## How to set up Census dataset search in Claude

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

### Use the Claude connector

1. **Add Spiral to Claude**: Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:

```text
https://api.spiral.ai/mcp
```

2. **Keep the detected sign-in and click Add**: Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.

3. **Click Connect**: The connector page opens. Connect takes you to Spiral in your browser.

### Use the Spiral skill

1. **Send Claude 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 Census dataset search**: 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": "census-gov/census/datasets",
    "input": {
      "vintage": 2000
    }
  }'
```

Then paste one of the prompts above: Claude finds Census dataset search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-desktop

## Census dataset search tools and prices

- [US Census Bureau · Datasets](https://spiral.ai/tools/alexandria/census-gov/census/datasets) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| query |  |  | Case-insensitive tokens all of which must appear in the dataset path, title or description. Required (>= 2 characters) when vintage is null. |
| cursor |  | — | next_cursor from the previous page. |
| vintage | 2000 to 2035 | — | Restrict to one vintage year (reads api.census.gov/data/{vintage}.json, ~0.5 s). Null searches the whole catalog (~5 MB, 5-10 s). |
| page_size | 1 to 25 | 20 | page_size |

## What can you do with Census dataset search in Claude?

Turn Census statistics into a county briefing with population trends and income or poverty comparisons. The assistant can identify the relevant datasets, places, and measures before explaining the estimates and their uncertainty.

### Maintain a county community report

Build a report for Travis County, Texas, with ACS characteristics, population history, and poverty estimates. Find the datasets and variable definitions, resolve county identifiers, check publication status, compare statewide collections, and retrieve the county details for the narrative.

### Prepare a grant needs assessment

Document population change, poverty, income, and housing conditions for a proposed county service area. Use statewide collections as benchmarks, local records as evidence, dataset and variable documentation to define measures, and publication checks to keep the assessment current.

### Compare counties for business expansion

Compare North Carolina counties using population trends, household income, poverty, and ACS housing characteristics. Identify the appropriate datasets, measures, and county codes; check publication changes; rank the county collections; then examine shortlisted counties in detail.

### Plan regional library outreach

Compare Montana counties for outreach planning using population change, poverty, and ACS characteristics. Resolve service-area counties, find and define the measures, check publication status, compare the statewide collections, and add local population and income detail to each county brief.

### Compare neighborhood characteristics

Compare ACS five-year housing measures across census tracts in Wake County, North Carolina. Find the dataset, inspect variable definitions, resolve the geographic hierarchy, and retrieve estimates with their margins of error.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Claude guides](https://spiral.ai/integrations/claude-desktop)

## Census dataset search in other agents

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

## More Claude guides

- [Census county poverty and income](https://spiral.ai/integrations/claude-desktop/census-county-poverty-and-income)
- [Census geography lookup](https://spiral.ai/integrations/claude-desktop/census-geography-lookup)
- [CelesTrak satellite orbit search](https://spiral.ai/integrations/claude-desktop/celestrak-satellite-orbit-search)
- [Census local population history](https://spiral.ai/integrations/claude-desktop/census-local-population-history)
- [CelesTrak satellite orbit by catalog number](https://spiral.ai/integrations/claude-desktop/celestrak-satellite-orbit-by-catalog-number)
- [Census population estimates collection](https://spiral.ai/integrations/claude-desktop/census-population-estimates-collection)

## Questions about Census dataset search in Claude

**Can Claude use Census dataset search?**

Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Census dataset search like any built-in tool.

**How much does Census dataset search cost in Claude?**

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

**Do I need an Alexandria account to use Census dataset search in Claude?**

No. Spiral runs Census dataset search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Census dataset search in Claude?**

About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.

**Does Claude wait while Census dataset search runs?**

Census dataset search runs in the background. Claude starts the run, checks on it and gives you the json when it's ready.

**How small an area can Census statistics describe?**

Coverage depends on the program and table. ACS five-year Detailed Tables reach block groups, while Subject Tables and Data Profiles reach census tracts; the SAIPE state and county files describe those larger jurisdictions.

**How current are Census estimates?**

Population estimates and SAIPE estimates are produced annually. An ACS five-year estimate combines 60 months of collected data, so its ending year does not make it a snapshot of that year alone.

**Why can an older population estimate change?**

Each new population estimates vintage revises the series back to the most recent census. The newest vintage supersedes previously published estimates for those dates, so a growth calculation should use one vintage throughout.

**Are poverty estimates exact counts?**

SAIPE uses statistical models to estimate income and poverty. Each state and county estimate is published with a 90% confidence interval, which matters when comparing counties with similar results.

**Why might an ACS one-year table omit a small community?**

Standard ACS one-year estimates cover areas with at least 65,000 residents. ACS five-year estimates cover all areas and are the appropriate product to investigate for smaller communities.

