Who Tb MCP server

@pipeworx/who-tb

WHO Global Tuberculosis Programme data — burden estimates, case notifications and programme financing for 217 countries, 2000 onward.

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

Tools

Estimates vs notifications

These answer different questions and are easy to confuse. Estimates (einc) are WHO's modelled view of how much TB exists, with uncertainty ranges. Notifications (c_newinc) are cases actually diagnosed and reported. The gap between them is undiagnosed TB, and quoting one as the other misstates a country's epidemic.

The dictionary is a first-class tool

The collection publishes its own data dictionary defining every column in every dataset. Field names like einc100k and budgetcppdstb cannot be guessed, and a wrong guess reports a wrong number silently — so it is exposed as a tool rather than left in a footnote.

Auth

None.

Data sources

(also notifications, budget, dictionary)

• WHO TME CSV endpoint — https://extranet.who.int/tme/generateCSV.asp?ds=estimates

• WHO Global Tuberculosis Report —

The endpoint takes only ds=; there is no server-side filtering, so whole files are fetched and filtered in the pack, memoised per isolate.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/who-tb/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_tb_estimates \
  -H 'Content-Type: application/json' \
  -d '{"country":"India","years":"2020-2023"}'

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

Shortened. The full README is on GitHub.