QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / USASpending.gov

USASpending.gov

Q: Is USASpending.gov MCP server safe?

QAmcp's test on 28 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. All 55 of its tools are labeled read-only. Overall it scored 75/100 on 28 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by 1102tools.com · https://usaspending.1102tools.com/mcp

USAspending.gov contracts, grants, loans, subawards, recipients, agencies, and federal accounts.

55 tools✓ all read-only✓ no account neededPricing: not listed

Visit website

75 /100

FAIL

12 of 12 checks · 28 Oct 2026

Is USASpending.gov MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
All 55 of its tools are labeled read-only.
Overall it scored 75/100 on 28 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

55 tools, in the server's own words.

search_awardsread-only

Search federal awards (contracts, IDVs, grants, loans, etc.) on USASpending.gov.

get_award_countread-only

Count awards matching filters, broken down by award category.

spending_over_timeread-only

Aggregate spending amounts over time, grouped by fiscal year, quarter, or month.

spending_by_categoryread-only

Aggregate spending by a dimension (top vendors, top agencies, top NAICS, etc.).

get_award_detailread-only

Fetch full details for a single award by its generated_internal_id.

get_transactionsread-only

Fetch the full transaction (modification) history for an award.

get_award_fundingread-only

Fetch File C funding data for an award: federal account, object class, program activity.

get_idv_childrenread-only

Fetch child awards (task/delivery orders) under an IDV.

lookup_piidread-only

Look up awards by their exact PIID, across contracts AND IDVs.

autocomplete_pscread-only

Autocomplete lookup for Product/Service Codes (PSC).

autocomplete_naicsread-only

Autocomplete lookup for NAICS codes.

list_toptier_agenciesread-only

List all top-tier federal agencies tracked by USASpending.

get_agency_overviewread-only

Get descriptive information for an agency: name, mission, website, data notes and DEF codes.

get_agency_awardsread-only

Get one obligation total and transaction count for an agency's awards in a fiscal year.

get_naics_detailsread-only

Get details for a NAICS code (2-6 digits).

get_psc_filter_treeread-only

Get the PSC hierarchy tree.

get_state_profileread-only

Get the federal award totals for recipients located in a US state.

search_subawardsread-only

Search FFATA subaward reports on USASpending.

spending_by_subaward_groupedread-only

Find matching prime awards and their cumulative FFATA report totals.

search_recipientsread-only

Search USASpending recipients (vendors and grantees) by keyword.

get_recipient_profileread-only

Get full profile for a recipient by their USASpending hash.

get_recipient_childrenread-only

Get the child recipients (subsidiaries) of a parent recipient.

autocomplete_recipientread-only

Find recipient names by partial name or UEI/DUNS.

list_statesread-only

List all states with their FIPS codes and award totals.

and 31 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

✕
Tools work with good inputs
47 failed
- ✕get_idv_children: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕lookup_piid: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕autocomplete_psc: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕autocomplete_naics: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕list_toptier_agencies: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕get_agency_overview: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕get_agency_awards: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- ✕get_naics_details: Its reply breaks the MCP rules, so AI apps can't read it: its reply has the wrong shape
- and 32 more
fail
✕
Bad inputs give a clean error
74 failed
- ✕get_award_funding: Broke the MCP rules on wrong type for "generated_award_id": its reply has the wrong shape
- ✕get_idv_children: Broke the MCP rules on missing required input "generated_idv_id": its reply has the wrong shape
- ✕get_idv_children: Broke the MCP rules on wrong type for "generated_idv_id": its reply has the wrong shape
- ✕lookup_piid: Broke the MCP rules on missing required input "piid": its reply has the wrong shape
- ✕lookup_piid: Broke the MCP rules on wrong type for "piid": its reply has the wrong shape
- ✕autocomplete_psc: Broke the MCP rules on missing required input "search_text": its reply has the wrong shape
- ✕autocomplete_psc: Broke the MCP rules on wrong type for "search_text": its reply has the wrong shape
- ✕autocomplete_naics: Broke the MCP rules on missing required input "search_text": its reply has the wrong shape
- and 32 more
fail
!
Every tool is described
50 warnings
- !search_awards: Description is very long (4176 characters), which uses up the AI's memory
- !search_awards: Inputs with no description: award_type, keywords, awarding_agency, awarding_subagency, funding_agency, recipient_name, naics_codes, psc_codes, set_aside_type_codes, extent_competed_type_codes, contract_pricing_type_codes, time_period_start,
- !get_award_count: Inputs with no description: award_type, keywords, awarding_agency, awarding_subagency, funding_agency, recipient_name, naics_codes, psc_codes, set_aside_type_codes, extent_competed_type_codes, contract_pricing_type_codes, time_period_start,
- !spending_over_time: Inputs with no description: group, keywords, awarding_agency, awarding_subagency, funding_agency, extent_competed_type_codes, contract_pricing_type_codes, recipient_name, naics_codes, psc_codes, award_type, time_period_start, time_period_en
- !spending_by_category: Inputs with no description: category, keywords, awarding_agency, awarding_subagency, funding_agency, recipient_name, extent_competed_type_codes, contract_pricing_type_codes, naics_codes, psc_codes, award_type, set_aside_type_codes, time_per
- !get_award_detail: Inputs with no description: generated_award_id
- !get_transactions: Inputs with no description: generated_award_id, limit, page, sort, order
- !get_award_funding: Inputs with no description: generated_award_id, limit, page, sort, order
- and 32 more
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !The tool list is about 78 KB (roughly 20k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
✓
ConnectsConnected in 480 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 55 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Fast enough
All good
- ✓Connecting took 480 ms
- ✓Listing tools took 100 ms
- ✓Average tool answer: 210 ms
- ✓get_transactions: Slowest tool: get_transactions (479 ms)
pass
✓
No secrets leakedChecked 136 error messages: no secrets or internal details
pass
✓
Resources and prompts work
All good ()
- –Could not list resources: the server limited our requests (HTTP 429)
- –Could not list prompts: the server limited our requests (HTTP 429)
pass
–
Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://usaspending.1102tools.com/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/com-1102tools-usaspending-gov-mcp.svg)](https://qamcp.dev/s/com-1102tools-usaspending-gov-mcp.html)

Score over time

28 Oct 202675

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use USASpending.gov, signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works