Check drug interactions from inside your agent.
Give Claude, ChatGPT, Cursor or any MCP client the Interaction Checker tools. Ask whether things can be taken together and it checks every pair against FDA prescribing labels, answering with the exact sentence and a link instead of guessing.
- Every pair checked, with a severity and the label sentence
- Pill appearances and sourced drug facts
- Free, no key, no sign-up
https://interaction-checker.com/mcpNo key and no sign-up. Paste the endpoint into your client.
claude mcp add --transport http interaction-checker https://interaction-checker.com/mcp
Name: Interaction Checker
Remote MCP server URL: https://interaction-checker.com/mcp
Name: Interaction Checker
MCP server URL: https://interaction-checker.com/mcp
Authentication: No authentication
{
"mcpServers": {
"interaction-checker": {
"url": "https://interaction-checker.com/mcp"
}
}
}
{
"servers": {
"interaction-checker": {
"type": "http",
"url": "https://interaction-checker.com/mcp"
}
}
}
codex mcp add interaction-checker --url https://interaction-checker.com/mcp
- Can I take ibuprofen with lisinopril?
- Check my list: metformin, atorvastatin, fish oil and grapefruit
- What does a 50 mg sertraline tablet look like?
Questions
What is an MCP server?
The Model Context Protocol is the open standard AI assistants use to call outside tools. Add this server to your client and your agent can use Interaction Checker directly.
Which clients work?
Any client that supports remote MCP servers: Claude, ChatGPT, Cursor, VS Code, Codex, Gemini CLI, Windsurf and more.
Does it cost anything?
No. It's free to use, with fair-use limits per address.
What happens to what I send?
It's used to answer the call, the same as a request on the website, and handled the way the privacy policy describes.
My client only runs local servers
Bridge it with mcp-remote: add a local server whose command is npx -y mcp-remote https://interaction-checker.com/mcp. Check that the URL ends in /mcp.
Is there a rate limit?
Yes, 10 requests per minute per address, shared with the REST API. That covers a conversation; if you are building something that needs more, request a higher limit on the API page.
How accurate is it?
As accurate as the FDA label wording it quotes, graded by the rule on the about page. Every result carries the sentence and a DailyMed link so you can check it. It is not medical advice, and a pair with nothing documented is not proven safe.