Skip to main content
Glama
pipeworx-io

fed-comms

Official
by pipeworx-io

@pipeworx/fed-comms

Federal Reserve communications as structured data: the FOMC meeting calendar with next_meeting, each post-meeting statement with the rate decision and vote parsed and a sentence-level redline against the previous statement, meeting minutes split into sections, Board speeches and testimony, and the Beige Book by district. Read from the Board of Governors' public pages and RSS feeds on federalreserve.gov.

Part of Pipeworx — an MCP gateway connecting AI agents to 1576+ live data sources.

Tools

  • fomc_calendar(year?) — every meeting of a year (scheduled, notation votes, unscheduled) with start/end dates, whether it has a Summary of Economic Projections, statement / implementation-note / press-conference / minutes URLs and the minutes release date, plus next_meeting with days_until and last_meeting with days_since. Answers "when is the next FOMC meeting".

  • fomc_statement(date?, compare_to?, include_text?) — the statement text, rate_decision (sentence, hold/cut/hike, target range as numbers, change in bp), vote (tally, named dissenters and what they preferred), the implementation-note URL, and diff_vs_prior: sentences changed (with the words removed/added), added, removed, computed against the previous statement with the vote tally, roll-call, date and media lines excluded. Answers "what changed in the latest Fed statement".

  • fomc_minutes(date?, section?) — the minutes with section headings (Developments in Financial Markets, Staff Review…, Participants' Views, Committee Policy Actions, Attendance); section is a case-insensitive substring filter. Answers "what did the minutes say about inflation".

  • fed_speeches(days?, speaker?, include_testimony?, limit?) — speeches and congressional testimony with speaker + official title, venue, URL and the opening paragraph. Answers "latest speech by Waller".

  • beige_book(edition?, district?) — the national summary or one district's report, split into sections (Labor Markets, Prices, and the district's industry sections). District accepts a city name, "Kansas City", "St. Louis", or the district number 1–12. Answers "what does the Beige Book say about Dallas".

Related MCP server: Federal Reserve Economic Data (FRED) MCP Server

Auth

Keyless.

Data sources

Gotchas the parser already handles: statements write ranges with a non-breaking hyphen (3‑3/4); the vote tally sits in the first paragraph ("by a 9 – 3 vote") since 2026, while older statements list every voter in "Voting for … were Jerome H. Powell, Chair; …" form; the calendar marks SEP meetings with * on the date and puts cross-month meetings under a "April/May" month label.

Quick Start

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

{
  "mcpServers": {
    "fed-comms": {
      "url": "https://gateway.pipeworx.io/fed-comms/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/fed-comms/mcp returns the tools in the table above plus the shared Pipeworx meta-toolsask_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 1576+ 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/fomc_calendar \
  -H 'Content-Type: application/json' \
  -d '{}'

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-fed-comms

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 Fed Comms data" })

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

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Retrieves, parses, and analyzes speeches and testimonies from Federal Reserve officers, enabling searches by speaker, topic, and keyword with automatic RSS feed discovery and intelligent relevance scoring.
    7
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Provides access to over 800,000 economic time series from the Federal Reserve, allowing users to browse, search, and retrieve data for indicators like GDP and unemployment. It supports custom date ranges and data transformations such as percentage changes or frequency aggregations.
    3
    317 npm
    120
    AGPL 3.0
  • A
    license
    A
    quality
    D
    maintenance
    Enables users to search, retrieve, and explore economic data series from the Federal Reserve Economic Data (FRED) API using natural language.
    11
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables pulling live Federal Reserve economic data (SOFR, Treasury yields, Fed funds rate, mortgage rates, CPI, PCE) for CRE capital markets analysis through an MCP client.
    6
    MIT