# ai.rxmanager/mcp (remote · mcp.rxmanager.ai)

Live US drug acquisition costs (CMS NADAC) for AI assistants. Free, no auth, weekly data.

- Trust score: 60/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.rxmanager.ai`: 60/100 (this document), [markdown](https://verifymcp.io/servers/ai-rxmanager-mcp/mcp.md), [page](https://verifymcp.io/servers/ai-rxmanager-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.rxmanager.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1069 tokens (~133/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-rxmanager-mcp https://mcp.rxmanager.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-rxmanager-mcp]
url = "https://mcp.rxmanager.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-rxmanager-mcp": {
      "type": "remote",
      "url": "https://mcp.rxmanager.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-rxmanager-mcp --url https://mcp.rxmanager.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-rxmanager-mcp:
    url: "https://mcp.rxmanager.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-rxmanager-mcp": {
      "type": "http",
      "url": "https://mcp.rxmanager.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 59, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 59, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 58)

First indexed and scored.

## MCP tools (8)

### `drug_price_lookup` (~113 tokens)

Look up the live public acquisition cost (CMS NADAC — National Average Drug Acquisition Cost) for a prescription drug in the United States: the per-unit price retail pharmacies actually pay to buy it, by strength, with the effective date. This is the honest baseline for judging what an employer health plan is charged by its PBM. Accepts a brand or generic name (e.g. "Gleevec", "imatinib", "atorvastatin").

Input parameters:

- `drug` (string, required): Brand or generic drug name

### `drug_search` (~67 tokens)

Search US prescription drugs by full or partial brand/generic name. Returns matching drugs with their generic name and brand names, so you can pick the right one before calling drug_price_lookup or drug_spread_check.

Input parameters:

- `query` (string, required): Full or partial drug name (min 2 characters)

### `drug_spread_check` (~163 tokens)

Compare what a US health plan was actually charged for a prescription fill against the live public acquisition cost (CMS NADAC) for the same quantity. Returns the acquisition cost, the amount charged, the gap, and the multiple. Use when someone asks "my plan paid $X for [drug] — is that high?". The gap is not all margin (a dispensing fee and claim administration are legitimate), but on most generics the legitimate part is a few dollars, not hundreds.

Input parameters:

- `amount_charged` (number, required): What the plan (or member) was charged for the fill, in USD
- `drug` (string, required): Brand or generic drug name
- `units` (number): Units in the fill (e.g. tablets). Default 30.

### `drug_shortages` (~107 tokens)

List current US prescription drug shortages from the FDA Drug Shortage Database (refreshed daily). Optionally filter by drug name or drug class. Returns the generic name, brand names, how long the shortage has been running, and how many manufacturers are affected. Useful for checking whether a drug a plan or patient depends on is in shortage before a refill or formulary decision.

Input parameters:

- `query` (string): Optional drug name or class to filter by (omit to list the most recent shortages)

### `medical_code_lookup` (~153 tokens)

Look up any US medical claim code across all major code sets at once: CPT (with 2025 RVUs), ICD-10-CM diagnoses, HCPCS Level II, MS-DRG payment groups, CARC denial reason codes (accepts EOB formats like CO-45 or PR-1), and place-of-service codes — plus Medicare MUE unit limits and NCCI bundling-edit counts. Official CMS/CDC/X12 data. Use when someone has a code from a medical bill, claim, EOB, or denial letter.

Input parameters:

- `code` (string, required): The code, e.g. 99213, E11.9, J1885, 470, or CO-45

### `drug_info_lookup` (~90 tokens)

Full profile of a US prescription drug by brand or generic name: identity and manufacturer, live CMS NADAC acquisition pricing, Medicare Part D spending and utilization, estimated pricing spread, and active clinical-trial pipeline. Broader than drug_price_lookup — use when someone wants the whole picture of a drug.

Input parameters:

- `drug` (string, required): Brand or generic drug name, e.g. Wegovy, metformin

### `pbm_term_explainer` (~112 tokens)

Plain-English explanation of pharmacy benefit (PBM) contract terms that drive employer plan cost: spread pricing, pass-through pricing, AWP, WAC, NADAC, MAC, rebates, rebate pass-through, effective rate guarantees, lesser-of logic, DIR fees, audit rights. Each explanation includes what to watch for in a contract. Call with a specific term, or without one to list all terms.

Input parameters:

- `term` (string): The contract term to explain (optional — omit to list all)

### `renewal_checklist` (~109 tokens)

Generate a dated preparation checklist for an employer pharmacy-benefit (PBM) contract renewal. Given the renewal date, returns what a plan sponsor should request and do at 120, 90, 60, and 30 days out — contract and exhibits, claims data, rebate reconciliation, benchmark review, and the decision record. Deterministic and vendor-neutral.

Input parameters:

- `renewal_date` (string, required): Renewal date, ISO format YYYY-MM-DD (e.g. 2027-01-01)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-rxmanager-mcp/mcp#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 59
- 2026-08-01: 59
- 2026-07-31: 59
- 2026-07-30: 61
- 2026-07-29: 60
- 2026-07-28: 60
- 2026-07-27: 59
- 2026-07-26: 58

## Links

- Remote endpoint: https://mcp.rxmanager.ai/mcp
- Website: https://rxmanager.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-rxmanager-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-rxmanager-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-rxmanager-mcp/mcp