
Connects Claude to the US Treasury's Fiscal Data API through the Pipeworx gateway. The source doesn't list specific tools, but Treasury Fiscal Data typically covers federal spending, revenue, debt, and budget datasets. You'd reach for this when building financial analysis workflows that need authoritative government fiscal data without writing API client code yourself. Works via streamable HTTP and includes an ask_pipeworx helper that lets you query in plain English instead of calling tools directly. Part of a larger gateway offering 673+ data sources, so you can add just this endpoint or connect to the full suite.
The U.S. Department of Treasury's Fiscal Data API. Daily Treasury cash, public debt outstanding, federal receipts and outlays, customs revenue, exchange rates, and savings bonds redemption data. The actual numbers behind "the federal deficit" and "the national debt." Free, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
For macro questions about the US fiscal stance — debt level, daily cash position, monthly receipts, customs revenue — Treasury Fiscal Data is the authoritative live source. Where FRED publishes monthly aggregates, Treasury publishes the underlying daily ledger.
Common flows:
treasury_debt → outstanding total broken into intragovernmental vs. public-held.treasury_customs_revenue({year: 2024}).Used by the trade_bilateral_analysis compound for tariff context.
None. Treasury Fiscal Data is fully public, free, no key.
| Dataset | Cadence | Use |
|---|---|---|
| Daily Treasury Statement | Daily | Cash position, deposits, withdrawals |
| Monthly Treasury Statement | Monthly | Receipts, outlays, deficit |
| Public Debt Outstanding | Daily | Total debt, intragovernmental vs. public-held |
| Customs Revenue | Monthly | Tariff collections |
| Treasury Reporting Rates of Exchange | Quarterly | Official rates for federal accounting |
| Savings Bond Securities | Monthly | Issuance, redemption |
Pipeworx caches with TTLs matching these.
exchange-rate or frankfurter packs.Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"treasury-fiscal": {
"url": "https://gateway.pipeworx.io/treasury-fiscal/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/treasury-fiscal/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 Treasury Fiscal data" })
The gateway picks the right tool and fills the arguments automatically.
MIT