@pipeworx/iati-datastore

International aid activities (IATI Datastore) — search every published aid and development activity worldwide by country, sector, donor or keyword, and read the individual commitments and disbursements behind it.

Part of Pipeworx — an MCP gateway connecting AI agents to 1865+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• iati_search_activities({ query, country, sector, reportingOrg, limit, offset, _apiKey }) — activities matching a Solr query, with convenience filters.

• iati_activity({ iatiIdentifier, _apiKey }) — the full record for one activity.

• iati_transactions({ iatiIdentifier, query, transactionType, limit, offset, _apiKey }) — the money actually moved: commitments vs disbursements, with dates and counterparties.

Related MCP server: mcp-iati

Auth

Platform key (PLATFORM_IATI_KEY) with BYO override via ?_apiKey=; sent upstream as an Ocp-Apim-Subscription-Key header. Free self-service registration at https://developer.iatistandard.org/ — sign up, then subscribe to the "IATI Datastore API" product. No manual approval step.

Data sources

• https://api.iatistandard.org/datastore/activity/select — activity index.

• https://api.iatistandard.org/datastore/transaction/select — transaction index.

IATI is the standard donor governments, UN agencies, development banks and large NGOs publish their aid spending to; the Datastore is the single queryable index over all of it.

Traps

• query is Apache Solr syntax, not free text. A bare word searches the default field only and quietly matches little; prefer an explicit field (title_narrative:water, recipient_country_code:KE). Every response echoes query_sent so you can see what actually ran.

• An activity with a budget may have no transactions. Not every publisher reports transaction-level detail, so an empty iati_transactions result is often a publisher gap, not a query error.

• Solr multi-valued fields come back as arrays and scalars do not, for the same field name across documents — the mapping normalises both.

• The populated payload is unverified — no fleet key exists. The Solr envelope (response.numFound / response.docs) is stable; document field names come from the published IATI field reference, and every tool returns raw so a caller with a real key is never blocked by a stale name here.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/iati-datastore/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 1865+ 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/iati_search_activities \
  -H 'Content-Type: application/json' \
  -d '{"country":"KE","limit":3}'

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

Run it from npm

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

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

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 Iati Datastore data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT