Skip to main content
Glama

@pipeworx/irs-afr

IRS Applicable Federal Rates (short, mid and long term, every compounding period, 110/120/130% variants, adjusted AFR) and the Section 7520 rate, for any month from the monthly IRS revenue ruling.

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • irs_afr(month?, term?, compounding?, percent?) — the AFR tables for a month: short-term (up to 3 years), mid-term (over 3 to 9) and long-term (over 9) at annual, semiannual, quarterly and monthly compounding, with the 110%, 120% and 130% variants (150% and 175% for mid-term) and the adjusted AFRs. Filters return a single rate. Answers "what is the November 2026 mid-term AFR, annual compounding?".

  • irs_7520_rate(month?) — the Section 7520 rate for valuing annuities, life estates, terms of years, remainders and reversions, plus the same ruling's section 382 long-term tax-exempt rate and low-income housing credit percentages.

Omit month for the newest published month. The IRS issues each month's rates in the preceding month (typically mid-month), so next month's rates are usually available from about the 15th. A month that has not been issued returns status: "not_yet_published" with the expected timing, never an empty result.

Every response carries ruling (e.g. "Rev. Rul. 2026-21"), data_as_of (the date the IRS published the ruling) and source.

Related MCP server: finology-student-loan

Auth

Keyless.

Data sources

  • IRS, Applicable Federal Rates revenue ruling — the monthly Internal Revenue Service revenue ruling that prescribes the AFR, adjusted AFR, section 382, low-income housing credit and Section 7520 rates. US federal government work, public domain. Each request reads the ruling live; nothing is copied.

Notes for maintainers: ruling numbers are not in month order (the month is read from the ruling's own text), and the IRS listing page lags the newest ruling and mislabels months, so it is used only as a hint and later numbers are probed directly.

Quick Start

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

{
  "mcpServers": {
    "irs-afr": {
      "url": "https://gateway.pipeworx.io/irs-afr/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/irs-afr/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 1856+ 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/irs_afr \
  -H 'Content-Type: application/json' \
  -d '{"month":"2026-11","term":"mid","compounding":"annual","percent":100}'

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-irs-afr

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 Irs Afr 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
    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
  • A
    license
    A
    quality
    B
    maintenance
    US federal student loan repayment math for AI agents, from a parity-verified engine rather than estimated. RAP, IBR, ICR, PAYE and tiered Standard payments with forgiveness timing and tax on forgiveness, plus the plans a borrower is excluded from and the rule why, such as Parent PLUS not qualifying for RAP. No key to start; keyed answers at mcp.finology.tech/mcp add citations.
    3
    77 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying Federal Reserve communications as structured data: FOMC meeting calendar, policy statements with parsed rate decisions, votes, and sentence-level redlines, minutes by section, speeches and testimony, and the Beige Book by district.
    0
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying US bank regulatory filings at line-item level: search institutions, retrieve labeled call reports, track specific items over time, compare banks, and inspect data coverage and code meanings, with amounts normalized to whole dollars.
    0
    MIT