# FDA Recall Monitor — Drugs, Devices & Food Safety (MCP) (`amygraphics/fda-recall-monitor`) Actor

openFDA official enforcement feed: drug, device & food recalls with Class I/II/III classification, reason, product, quantity and recalling firm. Filter by domain/class/firm/state/keywords. Monitor mode = daily digest of new recalls. No API key. MCP-ready.

- **URL**: https://apify.com/amygraphics/fda-recall-monitor.md
- **Developed by:** [Zakaria el bouami](https://apify.com/amygraphics) (community)
- **Categories:** Lead generation, Automation, MCP servers
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 💊 FDA Recall Monitor — Drugs, Devices & Food Safety (MCP)

> The full **openFDA enforcement feed**: every drug, medical-device and food recall reported by the FDA — with **Class I/II/III danger classification**, reason, product, quantity, recalling firm and distribution pattern. **Monitor mode = your daily "what got recalled yesterday" digest.** No API key. MCP-ready.

***

### ✨ The 6 things ChatGPT can't do (built in)

| Ingredient | Here |
|---|---|
| 🔒 **Hard-to-get data** | Official openFDA API chained across **3 endpoints** (drug + device + food enforcement) with report-date windows, paging and openFDA quirks handled (404 = no match, YYYYMMDD dates). 100% the official record. |
| 🛠️ **Hardest problems, solved** | Classification filter (Class I = serious/death risk), firm match, state match, ongoing-only, keyword scan over product+reason+brands. |
| ⚙️ **Automation** | `monitor` + daily schedule = **"every recall reported in the last 24h, deduped forever"** — QA teams, pharmacies, hospital procurement, food distributors and law firms pay real money for exactly this. |
| 🧠 **AI-agent cheap** | $0.001 start + $0.001 per recall — firm, reason, classification, everything free. |

> ⏳ **FDA lag intel (ChatGPT doesn't know this):** enforcement reports are published in weekly batches with a ~2-week delay. Default `daysBack=21` catches the full pipeline — a monitor scheduled daily quietly catches every batch the hour it lands.

***

### 🚀 3 recipes that pay

#### #1 — Daily safety digest (QA / compliance)

```json
{ "mode": "monitor", "daysBack": 7, "classifications": ["Class I", "Class II"] }
```

→ Schedule 07:00 → every serious recall reported yesterday across drugs, devices & food → Slack digest.

#### #2 — Competitor/supplier watch

```json
{ "mode": "monitor", "scopes": ["drug"], "firmIncludes": "Sterling", "daysBack": 3 }
```

→ The moment a tracked firm appears in an FDA recall record, you know.

#### #3 — Category radar (food distributors)

```json
{ "mode": "search", "scopes": ["food"], "keywords": "allergen", "daysBack": 60, "ongoingOnly": true, "maxResults": 200 }
```

→ All ongoing undeclared-allergen food recalls from the last 2 months.

**MCP**: `https://mcp.apify.com/?actors=amygraphics/fda-recall-monitor` — your agent answers *"any Class I medical-device recalls this week?"* with the official FDA record.

***

### 📦 What each row contains

`recallNumber` · `domain` (drug/device/food) · `eventId` · `status` (Ongoing/Completed/Terminated) · **`classification` (Class I/II/III)** · `recallingFirm` + `city`/`state`/`country`/`postalCode` · `productDescription` · **`reasonForRecall`** · `productQuantity` · `productType` · `codeInfo` (lot/serial ranges) · `distributionPattern` · `voluntaryMandated` · `initialFirmNotification` method · `recallInitiationDateISO` / `reportDateISO` / `centerClassificationDateISO` · **`lagDays`** (days between the recall event and its FDA batch publication — the two clocks, quantified) · `brandNames[]`/`genericNames[]` (openFDA harmonized, drugs) · `isNew`/`firstSeenAt` (monitor).

***

### 🆚 Competition

| Actor | Users | Monitor | 3 domains | Dedupe |
|---|---|---|---|---|
| benthepythondev/fda-recall-intelligence | 11 | partial | ❌ | ❌ |
| scrapers_lat/openfda-food-recalls | 5 | ❌ | food only | ❌ |
| **us** | — | ✅ schedule-ready | ✅ drug+device+food | ✅ KV forever |

***

### 🧪 Input reference

| Key | Default | What it does |
|---|---|---|
| `mode` | `search` | `monitor` = only recalls never returned before (KV `fdarecall-seen`, keyed domain+number) |
| `scopes` | all | `drug` / `device` / `food` |
| `daysBack` | 21 | report_date window (FDA lags ~2 weeks — don't go small) |
| `keywords`, `firmIncludes`, `stateIncludes` | — | client-side refinement |
| `classifications` | all | `Class I` / `Class II` / `Class III` |
| `ongoingOnly` | false | skip Completed/Terminated |
| `maxResults`/`maxPages` | 60 / 10 | caps (100/page/domain) |

**Fair use** — openFDA is the FDA's official public API (CC0 data). Anonymous rate limits are respected with polite pacing; heavy schedulers should self-throttle.

***

### 💰 Pricing

- **$0.001** actor start · **$0.001** per recall — classification, firm, reason, lot codes FREE

| Rows | Cost (us) |
|---|---|
| 60 recalls (monthly scan) | ~$0.06 |
| Daily all-FDA digest (30 days) | ~$1–3/month |

**Part of the AmyGraphics data empire** — 27 public actors: tenders (EU/US/UK), registers (UK companies, US funding, clinical trials, federal grants, regulations), conferences, trade shows, jobs & real estate. Contact: morocco.uiux@gmail.com · apify.com/amygraphics

# Actor input Schema

## `mode` (type: `string`):

search = window of recalls. monitor = only recalls never returned before (KV dedupe) — schedule daily/weekly.

## `scopes` (type: `array`):

drug / device / food — empty = all three.

## `daysBack` (type: `integer`):

FDA report_date window. NOTE: FDA enforcement reports lag ~2 weeks, so keep ≥14–21 for full coverage.

## `keywords` (type: `string`):

Client-side match on product + reason + firm + brand names (e.g. 'allergen', 'metal fragments', 'insulin').

## `firmIncludes` (type: `string`):

Client-side recalling-firm substring match (e.g. 'Olympus', 'Sterling').

## `classifications` (type: `array`):

Class I (serious/death risk) / Class II / Class III — empty = all.

## `stateIncludes` (type: `string`):

Client-side state substring match (e.g. 'CA', 'TX', 'NY').

## `ongoingOnly` (type: `boolean`):

Skip Completed/Terminated recalls.

## `maxResults` (type: `integer`):

Stop after this many recalls.

## `maxPages` (type: `integer`):

Hard cap on API pages per domain (100 recalls/page).

## `requestDelaySecs` (type: `number`):

Politeness pacing (anonymous openFDA is rate-limited).

## `proxyConfiguration` (type: `object`):

NOT needed — official API.

## Actor input object example

```json
{
  "mode": "search",
  "scopes": [
    "drug",
    "device",
    "food"
  ],
  "daysBack": 21,
  "keywords": "",
  "firmIncludes": "",
  "classifications": [],
  "stateIncludes": "",
  "ongoingOnly": false,
  "maxResults": 60,
  "maxPages": 10,
  "requestDelaySecs": 0.3,
  "proxyConfiguration": {}
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("amygraphics/fda-recall-monitor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("amygraphics/fda-recall-monitor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call amygraphics/fda-recall-monitor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,amygraphics/fda-recall-monitor"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/csODEkBA6sLhDBiY7/builds/ZFGdAzJoe2rTM4LrU/openapi.json