io.github.builtforai/loe-exposure is an MCP server published by io.github.builtforai, hosted at rxfinder.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 1 tool, including loss_of_exclusivity_exposure.
Drug patent expiries ranked by the Medicare Part D spending exposed to them
8 connections through 5 shared values. Tap any node.
Rank upcoming FDA Orange Book patent and exclusivity expiries BY the gross Medicare Part D spending exposed to them, with marketed-generic status for each ranked drug resolved from live CMS NADAC price evidence. Answers which expiries matter, not merely which come first. Reports EXPOSURE, never forecast savings. Spending is gross of manufacturer rebates. Orange Book small molecules only, so biologics — among the largest Part D line items — are excluded, and the headline total must not be read as spending that will "go generic".
| Parameter | Type | Description |
|---|---|---|
| limit | string | How many drugs to rank, default 25 |
| window | string | Months ahead to include, default 24 |
{
"name": "loss_of_exclusivity_exposure",
"description": "Rank upcoming FDA Orange Book patent and exclusivity expiries BY the gross Medicare Part D spending exposed to them, with marketed-generic status for each ranked drug resolved from live CMS NADAC price evidence. Answers which expiries matter, not merely which come first. Reports EXPOSURE, never forecast savings. Spending is gross of manufacturer rebates. Orange Book small molecules only, so biologics — among the largest Part D line items — are excluded, and the headline total must not be read as spending that will \"go generic\".",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "string",
"description": "How many drugs to rank, default 25"
},
"window": {
"type": "string",
"description": "Months ahead to include, default 24"
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.