Acquisition Forecasts MCP server

acquisition-forecasts

US federal agency procurement forecasts — what an agency has published its intention to buy, months to years before any solicitation exists. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1558+ live data sources.

This is the forward-looking surface. usaspending is money already obligated; govcon-intel scans SAM for solicitations already open. A forecast is the only one that answers "should I be staffing for this" rather than "did I miss it".

Tools

• forecastsearch(keyword?, agency?, subagency?, naics?, setaside?, fiscalyear?, min_value?, limit?)
• forecastdetail(forecastid, agency?) — full narrative, PoP, contacts
• forecast_agencies() — what is wired, and the verdict for everything that isn't

Coverage is one agency, and that is the finding

Agencies are required to publish forecasts and acquisition.gov indexes 22 of them. I probed every one on 2026-08-29. Exactly one publishes machine- readable data:

PDF forecasts are deliberately not OCR-ed. A parsed number that is wrong is worse than no number, and these are dollar values people plan against.

Because of that, forecastagencies() ships as a first-class tool and agenciescovered + coveragenote ride on every search response. A pack named for federal forecasts that quietly covered one agency would answer "nothing planned"* for 21 agencies it never checked — the absence-of-data-vs-absence-of- the-thing failure, which is the one this catalog keeps re-learning.

Adding an agency is a config entry in AGENCIES[] plus a field map.

Traps

The APFS API ignores every query parameter. ?naics=5415, ?organization=CBP and ?zzznonsense=x all return the identical 847 rows with the identical first id. There is no server-side filtering, so the pack fetches the whole file (~2 MB, cached 15 min) and filters in memory. Anyone "optimising" this by pushing filters upstream gets a result that looks filtered and is not.

smallbusinesssetaside and smallbusinessprogram are different fields. The first is a boolean (true/false/null), the second is the program name (SB, 8(a), HUBZone, WOSB, SDVOSB, AbilityOne, None, TBD). Coalescing the boolean first turns 350 of 847 rows into the literal string "true" and costs them their program name — and makes setaside="8(a)" return 27 rows instead of 71, because only rows whose boolean happened to be null could still match. They are returned as setaside (the name) and setasideapplies (the boolean, null meaning the row does not say*).

NAICS arrives as code and label in one string — "236220 - Commercial and Institutional Building Construction". Matching a caller's 5415 against the raw field would also hit any description containing those digits. The code is split out and matched as a prefix, which is how NAICS hierarchy works: 5415 covers 541511, 541512, … (175 rows vs 19 for the full code).

Values are bands, not numbers — "$50M to $100M", "Over $100M". The band text is preserved verbatim and parsed to low/high. For an open-ended top band high is null, not a large number, and min_value treats it as unbounded — a fabricated ceiling would be sortable and wrong.

organization is a sub-agency path, not an agency: CBP/OIT/LSS/ITB. All 847 rows are DHS. agency and sub_agency are reported separately so agency="DHS" means what a caller expects.

Shortened. The full README is on GitHub.