# FDA Warning Letters, Recalls & Enforcement Monitor (`schmarta/fda-warning-letters-recalls-monitor`) Actor Monitor FDA warning letters and drug/device/food recalls in one normalized feed. Company filters, 21 CFR citation extraction, LLM-ready letter text, delta-only monitoring. Works as an MCP server for AI agents. - **URL**: https://apify.com/schmarta/fda-warning-letters-recalls-monitor.md - **Developed by:** [Lucas Marta](https://apify.com/schmarta) (community) - **Categories:** AI, Automation - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $2.00 / 1,000 records This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. 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. Actors are written with capital "A". ## 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. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## FDA Warning Letters, Recalls & Enforcement Monitor Track **FDA warning letters** and **drug, device, and food recalls** in one normalized feed. Filter by company, subject keywords, issuing office, and date; extract full letter text as clean, **LLM-ready markdown** with **21 CFR citations** pulled out automatically; and run it on a Schedule in delta-only mode to get alerted the moment the FDA takes action against a company you care about. Regulatory-intelligence services charge thousands per year for this data. This Actor gets it straight from FDA.gov and openFDA — official, public-domain sources — for cents. ### How to monitor FDA warning letters 1. Pick your sources: warning letters, drug recalls, device recalls, food recalls. 2. Filter by company name (e.g. a competitor or supplier), subject keywords (`CGMP`, `sterility`, `listeria`, `510(k)`), or date range. 3. Turn on **Delta only** and create an Apify Schedule — every run returns only enforcement actions that are new since the last run. Wire the dataset into Slack, email, or your own pipeline with any Apify integration. ### What you get Each record is one dataset item, normalized across warning letters and recalls: | Field | Description | |---|---| | `recordType` | `warning-letter`, `drug-recall`, `device-recall`, `food-recall` | | `company` | Letter recipient or recalling firm | | `issuedAt` | Letter issue date / recall report date | | `subject` | Letter subject (e.g. "CGMP/Adulterated") or product description | | `classification` | Recall class: Class I, II, or III | | `cfrCitations` | Extracted 21 CFR citations (e.g. `21 CFR 211.22(d)`) | | `fullTextMarkdown` | Complete letter as clean markdown (when enabled) | | `letterUrl` | Link to the original letter on FDA.gov | | `isNew` | Whether this record is new since the last run | ### Who uses this - **Pharma / medical device regulatory affairs** — track FDA actions against competitors, suppliers, and CMOs - **Quality & compliance teams** — feed warning-letter trends (by CFR citation) into audit prep - **Food safety teams** — real-time recall monitoring by product keyword - **Investors & analysts** — FDA enforcement as a signal on public companies - **AI agents** — query FDA enforcement directly via MCP ### Use as an MCP server (AI agents) The Actor runs in Standby mode as a streamable-HTTP MCP server via [mcp.apify.com](https://mcp.apify.com): - `search_fda_enforcement` — search letters + recalls with company/keyword/date filters - `get_warning_letter_markdown` — any warning letter as clean markdown with CFR citations ### Pricing Pay per event — you only pay for what you extract: | Event | Price | |---|---| | Actor start | $0.005 | | Enforcement record | $0.002 | | Letter full text (markdown + CFR citations) | $0.015 | A daily delta-only monitor typically costs **well under $0.05 per run** — most runs return only a handful of new records. ### FAQ **Where does the data come from?** Warning letters come from FDA.gov's official listing; recalls come from the openFDA enforcement API. Both are US-government public-domain data. **How complete is it?** The warning-letter feed covers the full FDA archive (thousands of letters, updated as FDA publishes). Recalls cover drug, device, and food enforcement reports back to 2004. **Do I need an API key?** No. Optionally add a free openFDA key to raise rate limits for very large pulls. **Can I get only NEW enforcement actions?** Yes — that's delta-only mode. The Actor remembers what it already delivered for your exact filter combination. # Actor input Schema ## `sources` (type: `array`): Which FDA enforcement data to fetch. ## `companyName` (type: `string`): Filter to letters/recalls for companies whose name contains this text. ## `subjectKeywords` (type: `array`): Keep only records whose subject/product/reason contains any of these (e.g. `CGMP`, `sterility`, `listeria`). ## `dateFrom` (type: `string`): YYYY-MM-DD. ## `dateTo` (type: `string`): YYYY-MM-DD. Empty = today. ## `includeLetterFullText` (type: `boolean`): Fetch each warning letter and convert it to clean markdown with extracted 21 CFR citations — ready for AI/RAG pipelines. Charged per letter. ## `deltaOnly` (type: `boolean`): Return only records not seen in previous runs with the same filters. Ideal on a Schedule: get alerted only about NEW letters/recalls. ## `maxResults` (type: `integer`): Maximum records per run. ## `openFdaApiKey` (type: `string`): Raises openFDA rate limits from 1,000 to 120,000 requests/day. Free at open.fda.gov/apis/authentication. ## Actor input object example ```json { "sources": [ "warning-letters" ], "subjectKeywords": [], "dateFrom": "2026-01-01", "includeLetterFullText": false, "deltaOnly": false, "maxResults": 200 } ```` # 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 '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "dateFrom": "2026-01-01" }; // Run the Actor and wait for it to finish const run = await client.actor("schmarta/fda-warning-letters-recalls-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 '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "dateFrom": "2026-01-01" } # Run the Actor and wait for it to finish run = client.actor("schmarta/fda-warning-letters-recalls-monitor").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "dateFrom": "2026-01-01" }' | apify call schmarta/fda-warning-letters-recalls-monitor --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=schmarta/fda-warning-letters-recalls-monitor", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "FDA Warning Letters, Recalls & Enforcement Monitor", "description": "Monitor FDA warning letters and drug/device/food recalls in one normalized feed. Company filters, 21 CFR citation extraction, LLM-ready letter text, delta-only monitoring. Works as an MCP server for AI agents.", "version": "0.1", "x-build-id": "9nescf15Lo9usHKnY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/schmarta~fda-warning-letters-recalls-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-schmarta-fda-warning-letters-recalls-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/schmarta~fda-warning-letters-recalls-monitor/runs": { "post": { "operationId": "runs-sync-schmarta-fda-warning-letters-recalls-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/schmarta~fda-warning-letters-recalls-monitor/run-sync": { "post": { "operationId": "run-sync-schmarta-fda-warning-letters-recalls-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "sources": { "title": "📋 Sources", "type": "array", "description": "Which FDA enforcement data to fetch.", "items": { "type": "string", "enum": [ "warning-letters", "drug-recalls", "device-recalls", "food-recalls" ], "enumTitles": [ "Warning letters", "Drug recalls", "Device recalls", "Food recalls" ] }, "default": [ "warning-letters" ] }, "companyName": { "title": "🏢 Company name", "type": "string", "description": "Filter to letters/recalls for companies whose name contains this text." }, "subjectKeywords": { "title": "🔎 Subject keywords", "type": "array", "description": "Keep only records whose subject/product/reason contains any of these (e.g. `CGMP`, `sterility`, `listeria`).", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "📅 Issued after", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "YYYY-MM-DD." }, "dateTo": { "title": "📅 Issued before", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "YYYY-MM-DD. Empty = today." }, "includeLetterFullText": { "title": "🤖 Extract letter full text as LLM-ready markdown", "type": "boolean", "description": "Fetch each warning letter and convert it to clean markdown with extracted 21 CFR citations — ready for AI/RAG pipelines. Charged per letter.", "default": false }, "deltaOnly": { "title": "🔔 Delta only (monitoring mode)", "type": "boolean", "description": "Return only records not seen in previous runs with the same filters. Ideal on a Schedule: get alerted only about NEW letters/recalls.", "default": false }, "maxResults": { "title": "Max results", "maximum": 2000, "type": "integer", "description": "Maximum records per run.", "default": 200 }, "openFdaApiKey": { "title": "openFDA API key (optional)", "type": "string", "description": "Raises openFDA rate limits from 1,000 to 120,000 requests/day. Free at open.fda.gov/apis/authentication." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```