[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [DataSF dataset records](https://spiral.ai/integrations/antigravity/datasf-dataset-records)

# How to Use DataSF dataset records in Google Antigravity

Returns records or calculated summaries from a DataSF dataset. Use it to inspect permit activity, compare city service requests, or retrieve selected records for analysis.

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

## Prompts to try with DataSF dataset records in Google Antigravity

- Use DataSF dataset records to retrieve 100 Building Permits records filed during October 2026 and write a script that checks for repeated permit numbers.
- Use DataSF dataset records to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from DataSF dataset records and tell me what changed since last week.
- Check DataSF dataset records and summarize what you find in three bullet points.
- Pull the newest data from DataSF dataset records and give me the result as a table.

## How to set up DataSF dataset records in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 DataSF dataset records**: 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": "data-sf-gov/open-data/rows",
    "input": {
      "dataset_id": "<dataset_id>"
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds DataSF dataset records on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/antigravity

## DataSF dataset records tools and prices

- [DataSF open data portal · Rows](https://spiral.ai/tools/alexandria/data-sf-gov/open-data/rows) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| q |  | — | SoQL $q full-text search across all text columns. |
| group |  | — | SoQL $group; pair with aggregates in `select`. |
| limit | 1 to 50000 | 100 | Rows per page. The portal caps a request at 50000; wide datasets with geometry should use far less. |
| order |  | — | SoQL $order, for example `filed_date DESC` or `count(*) DESC`. Default `:id` when no `group` is given. |
| where |  | — | SoQL $where, for example `zoning_sim like 'RH-1%'`, `filed_date between '2026-09-01T00:00:00' and '2026-09-02T00:00:00'`, `intersects(the_geom,'POINT(-122.3966 37.7897)')`, `within_circle(point,37.7897,-122.3966,50)`. |
| cursor |  | — | Row offset to start from: the `next_cursor` of the previous page. Pattern: ^[0-9]{1,12}$. |

## What can you do with DataSF dataset records in Google Antigravity?

Build a San Francisco civic report backed by source definitions and queryable records. A coding agent can turn catalog discovery, schema inspection, and record counts into an analysis that fits your project's files.

### Build a permit activity briefing

Find permit sources through the catalog's categories and tags, inspect their definitions, count the selected period, and retrieve records for a monthly construction briefing. Account for permits that cover multiple addresses.

### Compare neighborhood service requests

Locate the 311 source through catalog discovery, verify its neighborhood and date definitions, and compare matching record totals with a breakdown of requests. Label the result as service requests.

### Prepare a scoped data extraction

Discover relevant tables using the catalog vocabulary, inspect their schemas, and count matching records before retrieving a defined date range. Use the result to populate a civic analysis project.

### Audit sources behind a civic report

Review the categories, search results, and dataset definitions behind a housing or city services report. Recalculate its record totals and retrieve supporting records so the published figures can be checked.

### Check permit counting assumptions

Inspect the Building Permits documentation, count records for a selected period, and examine repeated permit numbers. Establish whether a report needs address-level rows or a deduplicated permit total.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## DataSF dataset records in other agents

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

## More Google Antigravity guides

- [DataSF dataset details](https://spiral.ai/integrations/antigravity/datasf-dataset-details)
- [DataSF dataset search](https://spiral.ai/integrations/antigravity/datasf-dataset-search)
- [DataSF catalog categories and tags](https://spiral.ai/integrations/antigravity/datasf-catalog-categories-and-tags)
- [DataSF record count](https://spiral.ai/integrations/antigravity/datasf-record-count)
- [DC building permit search](https://spiral.ai/integrations/antigravity/dc-building-permit-search)
- [Earth Search Sentinel-2 image clip](https://spiral.ai/integrations/antigravity/earth-search-sentinel-2-image-clip)

## Questions about DataSF dataset records in Google Antigravity

**Can Google Antigravity use DataSF dataset records?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run DataSF dataset records like any built-in tool.

**How much does DataSF dataset records cost in Google Antigravity?**

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

**Do I need an Alexandria account to use DataSF dataset records in Google Antigravity?**

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

**How long does it take to set up DataSF dataset records in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while DataSF dataset records runs?**

DataSF dataset records runs in the background. Google Antigravity starts the run, checks on it and gives you the json when it's ready.

**Is every DataSF search result a dataset?**

No. The catalog can include tables, charts, maps, stories, and derived views. Check the result's type before choosing a source for record analysis.

**How fresh is DataSF data?**

Refresh schedules depend on the dataset. DataSF documents an approximately 10 a.m. daily refresh for 311 Cases, while DBI uploads Building Permits nightly.

**How much historical data is available?**

History depends on the selected dataset. For example, 311 Cases covers eligible cases created on July 1, 2008, or later.

**Does a row count equal the number of permits?**

Not necessarily. Building Permits can repeat one permit across multiple rows when it has multiple associated addresses, so counting rows can overstate the number of permits.

**Does DataSF guarantee the data is accurate?**

No. The city's terms say the data is subject to error and cannot be relied on without verification or a site inspection.

