
Wraps the Currents API to give Claude access to news data through a hosted gateway. Part of the Pipeworx platform, which aggregates 832+ data sources behind a single MCP interface. You can call individual tools directly or use the ask_pipeworx convenience method to query in plain English and let the gateway route to the right endpoint. The source doesn't list specific tools, but Currents API typically provides news search, filtering by category or region, and headline retrieval. Useful when you need current news data in your agent workflows without managing API keys or building wrappers yourself. Runs over streamable HTTP, so no local installation required.
Currents MCP — wraps the Currents API (currentsapi.services)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
latest_news | Get the most recent global news articles from Currents (70k+ sources). Filter by language and category. Example: latest_news({ language: "en", category: "technology", limit: 15 }) |
search_news | Search global news by keyword across Currents (70k+ sources). Filter by language, category, country, and date range. Example: search_news({ keywords: "artificial intelligence", language: "en", limit: 15 }) |
list_categories | List the news category labels supported by Currents (e.g. technology, business, world, sports). Example: list_categories({}) |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"currents": {
"url": "https://gateway.pipeworx.io/currents/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/currents/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Currents data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/currents_latest_news \
-H 'Content-Type: application/json' \
-d '{"language":"en","category":"technology","limit":15}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/currents_latest_news. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.