io.github.builtforai/coverage-exception is an MCP server published by io.github.builtforai, hosted at insurewith.ai. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including medicare_part_d_out_of_pocket_cap, medicare_coverage_restriction_and_exception.
Why Medicare Part D restricts a drug, and the exception and appeal path to challenge it
11 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Project month-by-month Medicare Part D out-of-pocket spending against the statutory annual cap, identify the month the cap is reached, quantify what the cap itself saves, and compare normal payment timing against the Medicare Prescription Payment Plan — which spreads the SAME total across the year without reducing it. Supports plan years 2026 and 2027 and fails closed to 2026 for any unsupported year rather than extrapolating. This is a standard-benefit simulation, NOT a plan-specific pharmacy quote: plan negotiated prices and plan cost sharing are not held and are never inferred.
| Parameter | Type | Description |
|---|---|---|
| drug | string | Optional drug name — checks formulary status and whether spending on it counts toward the cap |
| join | string | Optional month (1-12) the payment plan would be joined |
| year | string | Optional plan year: 2026 or 2027 |
| monthly * | string | Expected monthly out-of-pocket spend on covered drugs, in USD, e.g. "300" |
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.
| deductible | string | Optional plan drug deductible in USD, e.g. "615" or "0" |
{
"name": "medicare_part_d_out_of_pocket_cap",
"description": "Project month-by-month Medicare Part D out-of-pocket spending against the statutory annual cap, identify the month the cap is reached, quantify what the cap itself saves, and compare normal payment timing against the Medicare Prescription Payment Plan — which spreads the SAME total across the year without reducing it. Supports plan years 2026 and 2027 and fails closed to 2026 for any unsupported year rather than extrapolating. This is a standard-benefit simulation, NOT a plan-specific pharmacy quote: plan negotiated prices and plan cost sharing are not held and are never inferred.",
"inputSchema": {
"type": "object",
"required": [
"monthly"
],
"properties": {
"drug": {
"type": "string",
"description": "Optional drug name — checks formulary status and whether spending on it counts toward the cap"
},
"join": {
"type": "string",
"description": "Optional month (1-12) the payment plan would be joined"
},
"year": {
"type": "string",
"description": "Optional plan year: 2026 or 2027"
},
"monthly": {
"type": "string",
"description": "Expected monthly out-of-pocket spend on covered drugs, in USD, e.g. \"300\""
},
"deductible": {
"type": "string",
"description": "Optional plan drug deductible in USD, e.g. \"615\" or \"0\""
}
}
}
}For a drug on Medicare Part D, name the coverage problem — covered, prior authorization, step therapy, quantity limit, or not on formulary — and give the exception and appeal path with the CMS-named levels of appeal, who must submit the request, and what to ask the plan and the prescriber. Returns per-plan flag counts across plans held. Plan-specific clinical criteria and appeal deadlines are NOT held and are never inferred; they are returned in an explicit "unavailable" block rather than guessed.
| Parameter | Type | Description |
|---|---|---|
| drug * | string | Brand or generic drug name, e.g. "Humira", "adalimumab" |
| state | string | Optional 2-letter US state code, e.g. "TX" |
{
"name": "medicare_coverage_restriction_and_exception",
"description": "For a drug on Medicare Part D, name the coverage problem — covered, prior authorization, step therapy, quantity limit, or not on formulary — and give the exception and appeal path with the CMS-named levels of appeal, who must submit the request, and what to ask the plan and the prescriber. Returns per-plan flag counts across plans held. Plan-specific clinical criteria and appeal deadlines are NOT held and are never inferred; they are returned in an explicit \"unavailable\" block rather than guessed.",
"inputSchema": {
"type": "object",
"required": [
"drug"
],
"properties": {
"drug": {
"type": "string",
"description": "Brand or generic drug name, e.g. \"Humira\", \"adalimumab\""
},
"state": {
"type": "string",
"description": "Optional 2-letter US state code, e.g. \"TX\""
}
}
}
}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.