Skip to content
unzoi docs
Search and navigation
Start here
REST API
MCP
Limits and plans
Agent clients
SDKs
Guides

Recipes / Catch supply chain disruption before the wires

Catch supply chain disruption before the wires

/stories in semantic mode. This page is the operational half — what comes back, how it breaks, and what running it for real takes.

The request

GET /stories
  ?q=plant closure production halt shipping delay port congestion
  &mode=semantic
  &language=deu,jpn,zho,nld
  &from=<now - 7d>

As a call you can paste:

curl -s -G "https://api.unzoi.com/stories" \
  -H "x-api-key: $UNZOI_KEY" \
  --data-urlencode "q=plant closure production halt shipping delay port congestion" \
  --data-urlencode "mode=semantic" \
  --data-urlencode "language=deu,jpn,zho,nld" \
  --data-urlencode "from=<now - 7d>"

For an agent rather than a script, the same query is the list_stories MCP tool with these as its arguments.

Parameters used here

What comes back

Story clusters from the domestic press. Expect specifics — named facilities, revised timelines, named suppliers — that the eventual English coverage compresses into a sentence, if it appears at all.

Field by field: the /stories response reference.

How this goes wrong

Waiting for English coverage to confirm what a domestic outlet reported three days earlier. By the time the wire picks it up the information is priced in and the advantage is gone.

Adapting it

Add the languages that match your exposure rather than using the list above verbatim: Vietnamese and Indonesian for manufacturing shifts into Southeast Asia, Turkish for overland routes, Portuguese for Brazilian commodities. For a specific supplier, combine the language filter with the company name in hybrid mode and widen the window, since supplier-level coverage is sparse until something goes wrong.

Running it for real

Alert on the appearance of a story rather than on volume; by the time volume moves, the wire has it and the lead time is gone. Because domestic-language coverage arrives before confirmation, expect a higher false-positive rate than an English-only feed and budget human review accordingly. That trade is usually worth it — the cost of checking a few extra stories is lower than the cost of finding out three days late.

Why this approach

The case for these parameters over the obvious alternatives — and when this recipe is the wrong tool entirely — is on the recipe's page on unzoi.com. It is kept there rather than repeated here, so the argument and the operations cannot drift apart.