Skip to main content
Glama
pipeworx-io

cms-drug-price-negotiation

by pipeworx-io

@pipeworx/cms-drug-price-negotiation

The Medicare negotiated Maximum Fair Price (MFP) for every drug CMS has selected under the Inflation Reduction Act drug price negotiation program, by year, with an explicit "not selected" answer for any other drug.

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • mfp_lookup(drug, year?) — the MFP per 30-day equivalent supply for a brand name, generic/active ingredient or NDC (e.g. Enbrel, Farxiga, Ofev), for each year 2026-2028: in effect, ended by deselection, not yet effective, or selected with the price not yet published. A drug on no selected list returns selected: false with a plain statement, never a zero.

  • mfp_selected_drugs(ipay?) — every selected drug for an initial price applicability year (2026: 10 drugs, 2027: 15, 2028: 15 selected, prices not yet published) with its MFP by year.

Related MCP server: loupe

Auth

Keyless.

Data sources

  • CMS, Medicare Drug Price Negotiation Program, Selected Drug List and Maximum Fair Price data. US federal data, public domain.

The figures are a small table loaded from the gateway's key-value store, not fetched per request; every response carries data_as_of (the latest as-of date CMS stamps on the file). CMS reissues the data when it inflation-adjusts a price, deselects a drug or announces a cycle; refresh with node scripts/bake-index.mjs > src/mfp-index-data.ts and commit.

Notes for the next reader: the MFP is quoted per 30-day equivalent supply, not per unit or per package. Prices are inflation-adjusted each January, so a 2027 figure for a 2026-cycle drug differs from its 2026 figure. Stelara, Entresto, Xarelto and NovoLog/Fiasp are deselected, so their MFP ends 2026-12-31. Brand names are grouped as CMS groups them (for example Ozempic, Rybelsus and Wegovy share one MFP).

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "cms-drug-price-negotiation": {
      "url": "https://gateway.pipeworx.io/cms-drug-price-negotiation/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/cms-drug-price-negotiation/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1856+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/mfp_lookup \
  -H 'Content-Type: application/json' \
  -d '{"drug":"Enbrel"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/mfp_lookup. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-cms-drug-price-negotiation is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/cms-drug-price-negotiation/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "cms-drug-price-negotiation": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-cms-drug-price-negotiation"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Cms Drug Price Negotiation data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides unified access to drug formulary data from US ACA marketplace health insurance plans, enabling drug search, coverage details, restriction info, and plan comparison across thousands of plans.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Unifies five public US-government drug datasets into a single sourced page per GLP-1/cardiometabolic drug, providing cost, shortage, label, and alternatives. The MCP server exposes the same Drug contract as the UI for agent-native access.
    72,713,136 npm
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to access CMS Medicare Part D drug spending, prescriber, and pricing trend data through a single MCP tool with 15 actions, deployed on Cloudflare Workers for sub-50ms response times.
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Gives AI assistants live access to US prescription drug prices by pharmacy with observation dates, the free discount card, and vetted US equivalents of foreign-brand medicines, all through the Model Context Protocol.
    10
    45 PyPI
    MIT