Who Iris MCP server

@pipeworx/who-iris

Search WHO's published output — guidelines, technical reports, World Health Reports, weekly epidemiological records and governing-body documents — through IRIS, the Institutional Repository for Information Sharing.

Part of Pipeworx — an MCP gateway connecting AI agents to 1576+ live data sources.

Tools

Why downloads are a second call

Download URLs are not in the search response, and DSpace's embed= parameter does not carry them — bitstreams hang off the item's bundles. Fetching them for every hit would cost two extra requests per result for links most callers never open, so search returns the permanent handle URL and whoirisitem resolves real file URLs on demand.

The bundle nesting is deeper than it looks: each bundle's bitstreams is itself a paginated HAL collection, so files live at bundles[].embedded.bitstreams.embedded.bitstreams[].

Auth

None.

Data sources

• WHO IRIS (DSpace 7 REST) —
• IRIS front end —

Note: HEAD on a bitstream content URL returns 500; GET serves the PDF normally. That is a DSpace quirk, not a broken link.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/who-iris/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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 1576+ 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/who_iris_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"tuberculosis treatment guidelines","limit":3}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/whoirissearch. 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": {
    "who-iris": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-who-iris"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-who-iris

Shortened. The full README is on GitHub.