Openfda Database

Connects Claude to the openFDA database for querying drug, device, and food safety data maintained by the FDA. You'll want an API key (free to register) since the default 1,000 daily requests gets burned through fast in a session, but with a key you get 120,000. Built by Google DeepMind as part of their science skills collection. The setup checks licensing terms and uses their credentials protocol to safely handle the API key. Useful if you're building health research tools, need to pull adverse event reports, or want to analyze FDA datasets without manually navigating their API docs. Requires uv for Python environment management.

skills.sh installs: 2.3K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add google-deepmind/science-skills --skill openfda-database --agent claude-code

Installs into .claude/skills of the current project.

Files

openFDA Search and Query

Prerequisites

uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
User Notification: If .licenses/openfda_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://open.fda.gov/apis/ and https://open.fda.gov/license, then (2) create the file recording the notification text and timestamp.
.env file: Make sure the .env file exists in your home directory. Create one if it does not exist.
FDA_API_KEY (optional but recommended): Raises the daily request limit from 1,000 to 120,000. The skill works without it, but an agent can easily exhaust the keyless limit in a single session. You can register for a free key at https://open.fda.gov/apis/authentication/. You MUST use the safe credentials protocol in the credentials skill to check for and request this key if this skill looks relevant to the user's request.