[Integrations](https://spiral.ai/integrations) › [Grok](https://spiral.ai/integrations/grok) › [FDA medical device classifications](https://spiral.ai/integrations/grok/fda-medical-device-classifications)

# How to Use FDA medical device classifications in Grok

Returns device categories, product codes, regulatory classes, medical specialties, and classification regulations from FDA's Product Classification Database. Use it to understand a device category before researching specific products or approvals.

|  |  |
| --- | --- |
| Model | FDA medical device classifications |
| Available through | Alexandria |
| Category | Health |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FDA medical device classifications in Grok

- Use FDA medical device classifications to explain the glucose monitor categories you find. Show their product codes, regulatory classes, and classification regulations.
- Use FDA medical device classifications to find Class III cardiovascular device categories. List their names and product codes.
- Use FDA medical device classifications to look this up and give me the result as a table.
- Pull the latest numbers from FDA medical device classifications and tell me what changed since last week.
- Check FDA medical device classifications and summarize what you find in three bullet points.

## How to set up FDA medical device classifications 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 FDA medical device classifications**: 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": "fda-gov/devices/device_classifications",
    "input": {
      "skip": 0
    }
  }'
```

Then paste one of the prompts above: Grok finds FDA medical device classifications on Spiral, shows the price and runs it.

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

## FDA medical device classifications tools and prices

- [FDA · Device classifications](https://spiral.ai/tools/alexandria/fda-gov/devices/device_classifications) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| skip | 0 to 25000 | 0 | skip |
| limit | 1 to 100 | 25 | limit |
| device |  | — | Device name words, matched as a phrase, e.g. glucose monitor. |
| specialty |  | — | Medical specialty words, e.g. Clinical Chemistry or Cardiovascular. |
| device_class | 1, 2, 3, unclassified, not_classified, hde | — | device_class |
| product_code |  | — | Three-letter FDA product code, e.g. QBJ. Pattern: ^ *[A-Za-z]{3} *$. |

## What can you do with FDA medical device classifications in Grok?

Turn FDA device records into a readable product research brief with category definitions, labeled identities, and application decisions. A chat app can explain what each record establishes and organize the evidence around a specific device or manufacturer.

### Prepare a device category research brief

Explain a device category's classification, identify labeled products in that category, and summarize relevant PMA applications and supplements.

### Review a manufacturer's public device records

Compare a company's labeled brands and models with its PMA application records, then explain the product categories associated with the returned codes.

### Check a product research spreadsheet

Compare recorded device names, models, product codes, and PMA references against FDA records. Produce a discrepancy list for a researcher to review.

### Build a device market comparison

Organize competing devices by FDA category, compare their labeled product identities, and summarize available PMA decision histories without treating those histories as market share.

### Resolve a model from a device label

Look up a device identifier and compare the returned brand, company, and model with the label. Explain the meaning of its reported FDA product code.

## Overview

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

## FDA medical device classifications in other agents

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

## More Grok guides

- [FDA medical device adverse event reports](https://spiral.ai/integrations/grok/fda-medical-device-adverse-event-reports)
- [FDA medical device recall reports](https://spiral.ai/integrations/grok/fda-medical-device-recall-reports)
- [FDA food recall records](https://spiral.ai/integrations/grok/fda-food-recall-records)
- [FDA novel drug approvals](https://spiral.ai/integrations/grok/fda-novel-drug-approvals)
- [FDA first generic drug approvals](https://spiral.ai/integrations/grok/fda-first-generic-drug-approvals)
- [FDA orphan drug designation details](https://spiral.ai/integrations/grok/fda-orphan-drug-designation-details)

## Questions about FDA medical device classifications in Grok

**Can Grok use FDA medical device classifications?**

Yes. Add Spiral to Grok as an MCP server, and Grok can find and run FDA medical device classifications like any built-in tool.

**How much does FDA medical device classifications 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 FDA medical device classifications in Grok?**

No. Spiral runs FDA medical device classifications on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up FDA medical device classifications 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 FDA medical device classifications runs?**

FDA medical device classifications runs in the background. Grok starts the run, checks on it and gives you the json when it's ready.

**What does an FDA device record identify?**

Classification records describe a generic device category. UDI records identify labeled products and models, while PMA records describe premarket applications and supplements for Class III devices.

**How often is the device data refreshed?**

openFDA documents monthly updates for classification and PMA data, and weekly updates for UDI data. These are the API update schedules, so a recent source change may not appear immediately.

**How far back does the data go?**

openFDA lists 1976 as the earliest year for classification and PMA data, and 2013 for UDI data. Those dates describe dataset coverage, not a complete revision history for every record.

**Can a product code identify one specific device?**

A product code identifies a generic device category. Use a UDI record to distinguish a labeled brand or model, and a PMA record to investigate an application or supplement.

**Can I reuse FDA device data commercially?**

The classification and PMA datasets are marked public domain and CC0. GMDN content has separate restrictions: extracting it for specified commercial categorization, mapping, or AI training uses requires a GMDN Agency license.

