mcpField
M
Macro Snapshot

Macro Snapshot

Remote
pipeworx.ioFinance0Updated 2d ago

About Macro Snapshot

An MCP server for analysts and agents that need a concise view of the US and global economy. It combines FRED series with live cryptocurrency data into a structured snapshot and provides recent history for individual FRED series.

Key features

  1. 01Combine rates, inflation, and jobs indicators
  2. 02Show Treasury yields and curve spreads
  3. 03Include GDP, S&P 500, VIX, and BTC
  4. 04Report dates and freshness by data group
  5. 05Retrieve history for a FRED series

Use cases

  1. 01Get a quick overview of macroeconomic conditions
  2. 02Check yield-curve inversion and inflation status
  3. 03Review recent data for a snapshot indicator

MCP support

Exposes macro snapshot and individual FRED-series query tools to MCP clients through the Pipeworx gateway or a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/macro-snapshot/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-macro-snapshot

macro-snapshot MCP — the state of the economy in one call.

Part of Pipeworx — an MCP gateway connecting AI agents to 1882+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
macro_snapshotGet the current state of the US/global economy in ONE call — Fed funds rate, the full Treasury yield curve (3mo/2y/10y + 10y-2y and 10y-3m spreads with inversion flag), CPI & core CPI year-over-year, unemployment, nonfarm payrolls (+1mo change), real GDP growth, S&P 500, VIX, the broad USD index, and BTC. Composes 16 FRED series (Federal Reserve economic data) with live crypto, runs them in parallel, and returns a structured dashboard plus human-readable callouts (curve inversion, inflation vs the Fed's 2% target, elevated VIX). Use this instead of fetching ten indicators separately. No arguments. THE COMPONENTS DO NOT SHARE A DATE — daily series (rates, markets) sit beside quarterly GDP that can be 100+ days older; each group carries its own as_of map and freshness states the full span and oldest component — read those before comparing fields against the top-level as_of, which is only the newest daily series.
indicatorRead recent history for a single FRED (Federal Reserve economic data) series — drill into anything in the macro_snapshot or any other FRED series id. Common ids: UNRATE (unemployment), DFF (Fed funds), DGS10/DGS2/DGS3MO (Treasury yields), CPIAUCSL (CPI index), CPILFESL (core CPI index), PAYEMS (nonfarm payrolls), VIXCLS (VIX), SP500, MORTGAGE30US (30y mortgage rate), WALCL (Fed balance sheet), DTWEXBGS (broad USD index), T10Y2Y/T10Y3M (curve spreads). Returns observations most-recent-first plus the latest value.

Quick Start

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

{
  "mcpServers": {
    "macro-snapshot": {
      "url": "https://gateway.pipeworx.io/macro-snapshot/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/macro-snapshot/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 1882+ 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/macro_snapshot \
  -H 'Content-Type: application/json' \
  -d '{}'

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-macro-snapshot

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Macro Snapshot data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.