@pipeworx/aemps-cima

AEMPS CIMA — the Spanish Agency for Medicines and Health Products' public register of every medicine authorised for sale in Spain: brand/generic search, full authorisation detail, the structured ficha técnica (SmPC) and prospecto (patient leaflet) text, current supply shortages, and a changes-since-date feed.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Scope — Spain, and only Spain

Field values are Spanish (paracetamol, ibuprofeno, not US brand names). For the equivalent EU-wide register use ema-medicines; for the UK use mhra-uk; for the US use openfda. Tools are prefixed cima_ so they never win a generic drug question.

Tools

Auth

Keyless. No registration.

Data sources

• https://cima.aemps.es/cima/rest/medicamentos — search.
• https://cima.aemps.es/cima/rest/medicamento — detail by nregistro.
• https://cima.aemps.es/cima/rest/docSegmentado/contenido/{1|2} — segmented ficha técnica (1) / prospecto (2) text by nregistro.
• https://cima.aemps.es/cima/rest/psuministro — supply problems.
• https://cima.aemps.es/cima/rest/registroCambios — changes-since-date feed.

Things the next person would otherwise rediscover

• An unrecognised query parameter on /medicamentos is silently ignored, not rejected — you get the entire ~25,500-row register back, paginated, totalFilas unchanged. Measured: ?xxx=1 → totalFilas: 25455, identical to no filter. This pack only ever sends the confirmed filter set (nombre, practiv1, atc, laboratorio).
• /psuministro silently ignores laboratorio even though it's a field name on the response objects — ?laboratorio=Teva returns the same totalFilas (866) as no filter at all. Only nombre actually filters this endpoint.
• /registroCambios REQUIRES fecha, and rejects its absence with an HTTP 200 — {"error":"Es necesario indicar la fecha"}, not an HTTP error. A caller that only checks status code reads this as a clean empty success. fecha is dd/MM/yyyy, not ISO; an ISO date matches nothing. This pack accepts ISO from the caller and converts.
• Timestamps (estado.aut, estado.rev, fini, ffin, fecha) are epoch MILLISECONDS, converted to YYYY-MM-DD on the way out.
• The ficha técnica can run 25-30 sections. cima_medicine_document_sections caps total output around 40,000 characters (each section further capped ~4,000) and flags truncated: true per section rather than silently dropping content — pass seccion (e.g. "4.1") for one section only when you know which you need.
• Field values stay in AEMPS's own Spanish wording (labtitular, cpresc, comerc...) since that's what a Spanish-market query needs to match against; the pack adds English key names alongside the Spanish content rather than translating it.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/aemps-cima/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 1683+ 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/cima_search_medicines \
  -H 'Content-Type: application/json' \
  -d '{"ingredient":"paracetamol","limit":3}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-aemps-cima

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Aemps Cima data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT