usaspending mcp server
io.github.cyanheads/usaspending-mcp-server
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov.
— the operator's own registry description reported
Publisher io.github.cyanheads · first seen 2026-08-12 · endpoint https://usaspending.caseyjhand.com/mcp
Dependency rating derived
block — dead / unreachable · kind unknown · V n/a
Cluster unreachable · distinctiveness —. Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.
🔏 Signed receipt rr_ae0ffe769ea7113264fc6657 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.
● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →
History observed
Every probe we made, oldest → newest (5 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.
changelog (2 events)
| date | type | what changed |
|---|---|---|
| 2026-08-14 | outcome | http_error (was ok_tools) |
| 2026-08-12 | outcome | first probe: ok_tools |
What kind of tools these are derived
Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from the operator's own registry description — REPORTED, not observed (tools were not visible to the probe). What checking applies to each kind (the full methodology →):
| nature | tools | meaning | what checking applies |
|---|---|---|---|
| unclassified | 1 | not classifiable from its text | Tier-1 only until its tools describe themselves |
Tools last seen observed
Verifiability derived
answer key in hand V3W · confirmed
A public authority publishes the true answer AND we re-check this server against it today. The only grade under which “true” can ever be said. Assessed 2026-08-14T10:05:37Z (human:mrigank) · the full ladder: verifiability.
Harness readiness observed
Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.
| legibility check | tools passing | ok |
|---|---|---|
| name is clear & specific | 18/18 | ✓ |
| has a description | 18/18 | ✓ |
| description is substantive | 18/18 | ✓ |
| parameters are typed | 18/18 | ✓ |
| parameters are described | 18/18 | ✓ |
18 of 18 tools graded · 18 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.
Answer fidelity observed
usaspending_get_agency · get_agency · toptier 012 · FY2026 — re-derived against us-usaspending: every shared field matches — to the cent.
| field | server | primary | match |
|---|---|---|---|
| name | Department of Agriculture | Department of Agriculture | ✓ |
| fiscal_year | 2026 | 2026 | ✓ |
| budgetary_resources | 477289700104.5 | 477289700104.5 | ✓ |
| obligated | 184197612601.34 | 184197612601.34 | ✓ |
Drift observed
No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.
Looking for an alternative?
This server doesn't answer, but these live, allow-verdict servers describe themselves similarly — similar by what they say they do — never verified drop-in replacements; check each one before depending on it.
| server | verdict | shared terms |
|---|---|---|
| io.github.blackboxfoundry/livedatalink One key for 284 tools across 59 US public-data domains. Resale-safe government and open data. | allow | access, agency, award, federal |
| io.github.huwhitememes/tollbooth 37 paid x402 MCP tools for OSINT, prediction markets, web intel, and agent security on Base USDC. | allow | agency, award, federal, recipient |
| io.github.Th3Slack3r/slacking-biz 75 MCP tools: SEC financials, FRED economics, IRS 990, FDA, FX, UK Companies House. | allow | agency, award, federal, recipient |
| com.mactechsolutionsllc.www/federal-market SAM.gov contract opportunities and entity lookup (BYOK) plus USASpending federal award data. | allow | agency, award, federal, recipient |
| io.github.bch1212/pubrecords US public-records intelligence for AI agents — companies, SEC, courts, spending, licenses. | allow | access, agency, award, recipient |
raw probe records
| probed (UTC) | outcome | http | ms | protocol |
|---|---|---|---|---|
| 2026-08-14T19:59:28Z | http_error | 502 | 79 | |
| 2026-08-14T14:28:38Z | ok_tools | 200 | 111 | 2025-06-18 |
| 2026-08-14T11:40:45Z | ok_tools | 200 | 124 | 2025-06-18 |
| 2026-08-14T10:04:39Z | ok_tools | 200 | 118 | 2025-06-18 |
| 2026-08-12T05:34:41Z | ok_tools | 200 | 124 | 2025-06-18 |
Watch or embed this verdict
Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:
[](https://robinsaige.com/s/io.github.cyanheads/usaspending-mcp-server)
Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.