Federal Award Counterparty MCP Server
Pricing
from $50.00 / 1,000 tool calls
Federal Award Counterparty MCP Server
Answer questions about US federal award recipients from USAspending.gov: who won awards from an agency, one organisation's award history, and who that recipient actually is on the federal register.
Pricing
from $50.00 / 1,000 tool calls
Rating
0.0
(0)
Developer
NexGen Watch
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
3 days ago
Last modified
Share
Answer questions about US federal award recipients — who won awards from an agency, what one organisation has been awarded, and who that organisation actually is on the federal register — from USAspending.gov, live.
Built for sales teams qualifying government contractors, and for anyone who needs the award side of a counterparty before signing something.
Three things this server gets right that a naive read gets wrong
Every one of these was measured live against the source on 2026-07-30, and each one changes the answer.
1. "Last 12 months" does not mean "awarded in the last 12 months"
USAspending's default time filter matches awards with any activity in the window — so an old contract that saw a modification comes back as though it were new. Measured, same recipient, same 365-day window:
Asked "who won work from this agency last year", the first answer names incumbents from three
administrations ago. This server sends new_awards_only by default, states which clock
produced every answer, and makes you opt into the loose one by name.
2. A recipient name is a search key, not an identity
recipient_search_text is a fuzzy match. Measured: searching LOCKHEED returns
RAYTHEON/LOCKHEED MARTIN JAVELIN JV — a different legal entity. Every row reports the
name actually matched, and the tools point you at the UEI as the identity.
3. A parent and its children are different companies on this register
USAspending publishes a parent (P) and each child (C) as separate recipients, with separate
UEIs and separate totals. Measured on one trading name: three rows, three UEIs, totals of
$64.8bn, $27.0bn and $16.7bn. A single number for "the company" depends entirely on which
row you meant, so the level is always reported and the rows are never merged.
Tools
| tool | what it answers |
|---|---|
find_recipient | Recipients matching a name, each with UEI, parent/child level and total awarded |
get_recipient_profile | Full profile for one recipient: UEI, DUNS, business types, parent, location, lifetime totals |
get_award_history | Awards to one recipient in a trailing window, largest first |
get_agency_top_recipients | Who won awards from one federal agency in a trailing window |
list_agencies | Every top-tier agency, with the exact spelling the agency tool needs |
explain_limits | What this server will and will not say, and the three traps above. Read before acting. |
Award families: contracts (default), grants, direct_payments, loans, other. An
unrecognised family is refused rather than silently defaulted.
Scope
US federal PRIME awards published on USAspending.gov. One jurisdiction. Every query sends
subawards=False, so a subcontractor on a federal prime contract does not appear here and this
server does not imply otherwise.
This server reports what USAspending publishes. It does not certify that an organisation is or is not a federal contractor, does not decide that two similarly named recipients are the same entity, and says nothing about award performance, quality or compliance.
Source, public and logged-out, no key: api.usaspending.gov/api/v2. robots.txt on that host
is 404 — no Disallow and no Crawl-delay — and every outbound call is paced anyway through one
shared strict-pacing bucket at 5 requests/second.
Pricing
| Event | Price |
|---|---|
Server start (apify-actor-start) | $0.05, charged once per server run by the platform |
Tool call (mcp-tool-call) | $0.05 flat per completed tool call |
No other events. Memory is pinned to 1024 MB so the start fee is charged once — on this platform the start event bills once per gigabyte.
Errors and notices are not charged. An empty name, an unknown award family, or a USAspending read failure returns without billing.
A sourced "no results" IS charged. Zero rows from a successful read is the honest answer to the question asked — the register publishes nothing matching — and it is billed as an answer, not given away as a failure.
If a tool call cannot be billed correctly, the call fails rather than serving free.
