USASpending MCP
A Model Context Protocol server that wraps the USASpending.gov REST APIs as deterministic tool calls. Built for federal contracting officers, GS-1102 contract specialists, contract analysts, market research teams, and small business government contractors who need plain-English access to federal spending and award data.
55 tools, the deepest USASpending coverage of any public MCP. Hardened across multiple live audit rounds against production endpoints, plus Hypothesis-driven property tests. MIT licensed. No API key required.
What it does
Award Search
- Search awards across all federal agencies by NAICS, PSC, set-aside type, fiscal year, vendor, recipient, agency
- Geographic filters: place of performance state, county, congressional district, country, recipient location
- Time-window filters: action date, award date, period of performance start/end
- Returns ceiling, obligated, contract type, set-aside, NAICS, PSC, agency hierarchy
Award Detail and Lookups
- Lookup by PIID (contracts), FAIN (assistance awards), URI, or generated unique award ID
- Award detail rollups across base + options + modifications
- Award funding by federal account, object class, program activity, fiscal year
- Transaction-level history showing every obligation event over the life of the award
- Sub-award rollups linked to prime award
FFATA Subawards
- Subaward search across all FFATA reporting recipients
- Acquisition subcontracts and assistance grant subawards
- Subaward detail with prime award linkage
Recipient Profiles
- Lookup by name, recipient unique ID, or DUNS legacy
- Recipient hierarchy (parent, child, branch, division)
- Recipient award history broken down by agency, NAICS, PSC, fiscal year
Agency Depth
- Toptier agency overview (overall budget, obligations, top recipients, top NAICS)
- Sub-agency listings under any toptier agency
- Federal accounts owned by an agency
- Object class and program activity breakdowns
- Agency awards filtered by any tier of the hierarchy
Spending Analytics
- Spending by category: recipient, agency, sub-agency, federal account, program activity, object class, NAICS, PSC, state, county, district, country
- Spending over time: monthly, quarterly, fiscal year buckets
- Aggregate counts and totals across any filter combination
Geographic Search
- State profiles with award totals and top recipients
- Filter awards by place of performance or recipient location
- Cross-state spending comparisons
IDV (Indefinite Delivery Vehicle) Depth
- IDV child orders and ceiling burn
- Track task orders against ceiling
- Vehicle utilization by year and agency
Code Lookups
- NAICS autocomplete, full-text search, hierarchy, and detail
- PSC autocomplete, filter tree, free-text search
- Agency toptier and subtier listings
Federal Accounts
- Treasury federal account lookups
- Federal account spending breakdowns by object class and program activity
Use cases
- Pre-award market research (FAR Part 10): see who's been winning what at which agencies
- Vendor due diligence: pull a vendor's full federal award history before negotiation or teaming
- Competitive intelligence: identify primes holding IDIQ vehicles in your NAICS for teaming
- Set-aside research: 8(a), SDVOSB, WOSB, HubZone award patterns
- Spending oversight: agency rollups for OIG/GAO reviews
- Small business: find opportunities to sub on existing IDIQs
Compatibility
- Claude Desktop (one-click .mcpb install or Copy JSON)
- Codex (ChatGPT) via TOML config or codex mcp add
- Gemini CLI via ~/.gemini/settings.json
- Copilot via .vscode/mcp.json in VS Code
- Claude Code, Cursor, Cline, Zed, Continue, and any other MCP-compatible client
Install
No API key required.
{
"mcpServers": {
"usaspending-gov": {
"command": "uvx",
"args": ["--refresh-package", "usaspending-gov-mcp", "--from", "usaspending-gov-mcp", "usaspending-mcp"]
}
}
}
TOML config (Codex):
[mcp_servers.usaspending]
command = "uvx"
args = ["--refresh-package", "usaspending-gov-mcp", "--from", "usaspending-gov-mcp", "usaspending-mcp"]
PyPI: pip install usaspending-gov-mcp or uvx --from usaspending-gov-mcp usaspending-mcp
Example prompts
- "Show me the top 10 AFRL contracts awarded in FY2025 by dollar value, with vendor, amount, and description."
- "Pull the 12-month award history for Leidos. Break down by agency, NAICS, and ceiling vs obligated amounts."
- "Who is winning 8(a) awards at DHS in the last fiscal year, and for how much?"
- "Show me all SDVOSB awards across the federal government in FY25 under NAICS 541512."
- "Pull all subawards from prime PIID HQ003424F0042. Who got what and for how much?"
- "Find IDIQ vehicles at DoD under NAICS 541512 awarded in the last 24 months so I can see which primes I could team on."
- "Break down NAVSEA spending in FY25 by NAICS and recipient."
- "Compare CECOM and AFRL spending under PSC R408 over the last three fiscal years."
- "Pull the full transaction history for award PIID W912DY24F0123, including every modification and obligation event."
Hardening
Independently hardened across multiple live audit rounds against production USASpending endpoints, plus Hypothesis-driven property tests. Each release ships a testing.md documenting bugs found and fixed during hardening. Pydantic models use extra="forbid" to surface API drift instead of silently dropping fields. Defensive response parsing guards against partial outages, schema changes, and pagination edge cases.
Source
- GitHub: https://github.com/1102tools/federal-contracting-mcps/tree/main/servers/usaspending-gov-mcp
- PyPI: https://pypi.org/project/usaspending-gov-mcp/
- Docs and install walkthrough: https://1102tools.com/install
- Part of the 1102tools suite: 8 federal contracting MCPs + 6 Claude Skills (SOW/PWS Builder, IGCE Builder FFP, IGCE Builder LH/T&M, IGCE Builder CR, OT Project Description Builder, OT Cost Analysis)
- License: MIT
Server Config
{
"mcpServers": {
"usaspending-gov": {
"command": "uvx",
"args": [
"--refresh-package",
"usaspending-gov-mcp",
"--from",
"usaspending-gov-mcp",
"usaspending-mcp"
]
}
}
}