Sfda Drugs MCP Server

@pipeworx/sfda-drugs

Saudi Food and Drug Authority (SFDA) MCP — Saudi Arabia's drug regulator: registered human drugs with official SAR prices, current drug shortages, recent drug approvals, clinical trials running in the Kingdom, and registered drug companies/manufacturers. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1866+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• sfda_drug_search(query?, start_page?, pages_to_scan?) — registered drugs with official prices (SAR). Scans a bounded window of the ~1,400-page list and filters locally by scientific or trade name; returns a next_page cursor to continue.
• sfda_drug_details(nid, id) — the full SFDA record for one list entry: register number, ATC code, package size, shelf life, price, and the rest of the details page.
• sfda_drug_shortages(scientific_name?, trade_name?, registration_no?, agent_name?, page?) — current shortage list; server-side filters work here.
• sfda_drug_approvals(scientific_name?, trade_name?, page?) — recent drug approvals, newest first.
• sfda_clinical_trials(title?, drug?, sponsor?, protocol_number?, phase?, status?, site?, page?) — SFDA-registered clinical trials with sponsor, phase, protocol number and hospital site.
• sfda_drug_companies(name?, registration_no?, production_line?, country?, page?) — registered drug companies and manufacturing sites worldwide.

Auth

None. All five lists are public server-rendered HTML on www.sfda.gov.sa — no key, no login, no CAPTCHA on the data pages. The formal API host (developer.sfda.gov.sa) was unreachable when this pack was built and is not used.

Notes and traps (verified live 2026-09-07)

• The drugs-list search is broken on the SFDA side. /en/drugs-list ignores every filter parameter (ScientificName, TradeName, …) on both GET and the site's own POST flow, in both locales — the parameter is echoed into the form and pager but never applied. sfda_drug_search therefore filters client-side over a bounded page window. The other four lists apply their filters server-side correctly.
• ?page=0 is not the first page. The bare URL is page 0; ?page=0 returns a different, unrelated slice. The pack omits the parameter for page 0.
• Blank approval_date on the newest approvals is a source gap, not a scraping miss — older pages (e.g. page 20) carry real dates like 2025-08-01; the newest rows are published before their date is.
• Arabic enum values in otherwise-English tables. Shortage status (غير متوفر = not available), company status (مسجلة = registered), drug type (بشرية = human) and country names render in Arabic. The pack translates known enums to English and keeps the original in *_ar fields. The companies country filter only matches the Arabic value.
• Array as a field value on details pages is a rendering bug on the SFDA side (a PHP array printed raw); the pack returns those fields as null.
• Certificate issue dates on the companies list are Hijri calendar (e.g. 1430-03-01), not Gregorian.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/sfda-drugs/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 1866+ 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/sfda_drug_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"zantac","pages_to_scan":3}'

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

Run it from npm

@pipeworx/mcp-sfda-drugs 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/sfda-drugs/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "sfda-drugs": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-sfda-drugs"]
    }
  }
}

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 Sfda Drugs data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT