[Integrations](https://spiral.ai/integrations) › [Grok](https://spiral.ai/integrations/grok) › [Socrata dataset records](https://spiral.ai/integrations/grok/socrata-dataset-records)

# How to Use Socrata dataset records in Grok

Fetch records or calculated summaries from a public Socrata dataset, such as building permits or 311 requests. Use it when you need matching rows, category counts, or date-based comparisons.

|  |  |
| --- | --- |
| Model | Socrata dataset records |
| 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 Socrata dataset records in Grok

- Use Socrata dataset records for Chicago's Building Permits dataset ydr8-5enu to compare permit counts by permit type for January through March 2025.
- Use Socrata dataset records for NYC's 311 dataset erm2-nwe9 to show the ten most common complaint types in October 2026, with a count for each.
- Use Socrata dataset records to look this up and give me the result as a table.
- Pull the latest numbers from Socrata dataset records and tell me what changed since last week.
- Check Socrata dataset records and summarize what you find in three bullet points.

## How to set up Socrata dataset records in Grok

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

### Use the Grok connector

1. **Add a custom connector**: In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.

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

2. **Sign in to Spiral and approve**: Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.

3. **Check that it is connected**: Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.

### Use the Spiral skill

1. **Send Grok 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 Socrata 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": "socrata-com/open-data/query_dataset",
    "input": {
      "portal": "<portal>",
      "dataset_id": "<dataset_id>"
    }
  }'
```

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

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

## Socrata dataset records tools and prices

- [Socrata open-data portals · Query dataset](https://spiral.ai/tools/alexandria/socrata-com/open-data/query_dataset) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| q |  | — | Full-text search across the dataset's text columns. |
| group |  | — | SoQL $group, e.g. `permit_type` (with an aggregate in select). |
| limit | 1 to 1000 | 100 | Rows per page (1-1000). A page is also cut at about 1 MB of row data; continue from next_offset. |
| order |  | — | SoQL $order, e.g. `issue_date DESC`. Defaults to the row id `:id` for stable paging (none for aggregates). |
| where |  | — | SoQL $where without the keyword. String literals in single quotes ('O''Hare' escapes a quote). E.g. `issue_date >= '2024-01-01' AND permit_type = 'PERMIT - NEW CONSTRUCTION'`, `within_circle(location, 41.88, -87.63, 500)`. |
| offset | 0 to 100000000 | 0 | Row offset (next_offset of the previous page). |

## What can you do with Socrata dataset records in Grok?

Answer a local-government question with a published table and a clear coverage boundary. A chat app can identify relevant Socrata sources, explain their columns, and summarize permit or service-request data in plain English.

### Compare building-permit activity

Find Chicago's Building Permits table, inspect its permit categories and date columns, then compare monthly counts. Keep the dataset's exclusion of voided and revoked permits in the analysis.

### Plan a 311 service-demand report

Locate NYC's 311 source table, check the available agency and problem columns, and summarize requests by category. Use the results to identify which published request types account for the largest volumes.

### Check whether a historical comparison is possible

Find candidate government tables, inspect their descriptions and date columns, then measure their actual date ranges. Establish the available history before proposing a multiyear trend report.

### Choose a source for a civic dashboard

Find tables for the dashboard's topic, compare their publisher information and schemas, and retrieve sample summaries. Choose a source whose published columns support the intended charts.

### Maintain a municipal data pipeline

Locate the published table, inspect its current columns, and retrieve the records needed by a report. Compare schemas between runs so a renamed or changed column gets reviewed before the next report.

### Prepare a sourced local-government briefing

Find relevant permit or service-request tables, document what each row represents, and calculate the requested totals. Include the publisher's coverage limits alongside the figures.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Grok guides](https://spiral.ai/integrations/grok)

## Socrata dataset records in other agents

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

## More Grok guides

- [Socrata dataset details](https://spiral.ai/integrations/grok/socrata-dataset-details)
- [Socrata dataset search](https://spiral.ai/integrations/grok/socrata-dataset-search)
- [SAM.gov registration changes](https://spiral.ai/integrations/grok/sam-gov-registration-changes)
- [Supreme Court of Canada citation lookup](https://spiral.ai/integrations/grok/supreme-court-of-canada-citation-lookup)
- [SAM.gov registered business search](https://spiral.ai/integrations/grok/sam-gov-registered-business-search)
- [Supreme Court of Canada judgment list](https://spiral.ai/integrations/grok/supreme-court-of-canada-judgment-list)

## Questions about Socrata dataset records in Grok

**Can Grok use Socrata dataset records?**

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

**How much does Socrata dataset records cost in Grok?**

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

**Do I need an Alexandria account to use Socrata dataset records in Grok?**

No. Spiral runs Socrata 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 Socrata dataset records in Grok?**

About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.

**Does Grok wait while Socrata dataset records runs?**

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

**Does Socrata cover every government open-data portal?**

The documented search boundary is public Socrata-hosted government data. It can search across publishers or within one portal, so it should not be treated as a directory of every government's open data.

**How can I distinguish a data update from a description change?**

Socrata reports data-update and metadata-update times separately on dataset landing pages. Use that distinction when assessing freshness: a description edit and a change to the underlying records are separate events.

**Does a full dataset replacement mean every record changed?**

Socrata warns that a full replacement updates every record's system timestamp. A timestamp-based comparison can therefore report the entire table as changed after a replacement.

**How much Chicago building-permit history is available?**

Chicago's Building Permits dataset covers permits issued from 2006 to the present. It excludes permits voided or revoked after issuance, so it is not a complete archive of every permit ever issued.

**How fresh are NYC's published 311 requests?**

NYC says its 311 Service Requests from 2020 to Present dataset updates daily. It also warns that values in many fields change over time, so previously retrieved requests can have different values later.

