# Drug & Product Safety MCP Server (`tributarydata/drug-safety-mcp`) Actor

Official FDA recalls, drug labelling, adverse event reports and ClinicalTrials.gov studies as MCP tools for AI agents. Every answer cites its source.

- **URL**: https://apify.com/tributarydata/drug-safety-mcp.md
- **Developed by:** [Tributary Data](https://apify.com/tributarydata) (community)
- **Categories:** MCP servers, Agents, Other
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $15.00 / 1,000 tool calls

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/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — 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

## Drug & Product Safety MCP Server

Give your AI agent direct access to **FDA recall, labelling and adverse-event data** plus **ClinicalTrials.gov**, so it can answer safety questions from official records rather than memory.

Every response includes a `source` pointing at the official dataset.

### What it answers

- *"Has this drug been recalled, and how serious was it?"*
- *"What does the official FDA label say about warnings for this medication?"*
- *"What adverse reactions are most reported for this drug?"*
- *"Has this brand of food been subject to a recall?"*
- *"What clinical trials are recruiting for this condition?"*

### Tools

| Tool | What it does |
| --- | --- |
| `search_drug_recalls` | FDA drug recalls, with severity class and what that class means |
| `search_food_recalls` | FDA food recalls by product, brand or firm |
| `search_device_recalls` | FDA medical device recalls |
| `get_drug_label` | The official FDA label: indications, dosage, warnings, boxed warnings, contraindications |
| `adverse_event_summary` | Most frequently reported adverse reactions, across 20M+ reports |
| `find_clinical_trials` | ClinicalTrials.gov studies by condition, intervention and recruiting status |

### Built to be read correctly

Safety data is easy to misreport, so this server ships context alongside the numbers:

- **Recall severity is explained, not just labelled.** A "Class I" recall returns the FDA's actual meaning — reasonable probability of serious harm or death — rather than a code the agent has to guess at.
- **Adverse event counts carry a caveat in the response.** These are voluntary reports. They do not establish that a drug caused a reaction, and volume is heavily influenced by how widely a drug is prescribed. That warning travels with the data so it cannot be quietly dropped.

### Why the data is trustworthy

All FDA data comes from openFDA, the agency's own public API. Trial data comes from ClinicalTrials.gov, run by the US National Library of Medicine. No third-party aggregators.

### Pricing

$0.004 per tool call. No subscription, no minimum.

### Limits and honesty

- **US FDA data only.** A product not recalled in the US may still be recalled elsewhere.
- openFDA data is not real-time; there is a lag between an action and its appearance in the API.
- Labels are the manufacturer's submitted content. Multiple labels may exist for one generic drug; this returns the closest match.
- **This is not medical advice.** It reports what regulators published. Clinical decisions need a clinician.

# Actor input Schema

## Actor input object example

```json
{}
```

# Actor output Schema

# 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("tributarydata/drug-safety-mcp").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("tributarydata/drug-safety-mcp").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 tributarydata/drug-safety-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tributarydata/drug-safety-mcp"
        }
    }
}

```

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/b96PxRFfzEQCeaq3o/builds/wNl4XEPLwVYVb1u9w/openapi.json