USAspending MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| USASPENDING_TIMEOUT_MS | No | Request timeout in milliseconds for API calls. Default is 30000. | 30000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| usaspending_list_toptier_agenciesA | List federal toptier agencies with current USAspending budgetary, obligation, and outlay summary fields. No authentication required. |
| usaspending_autocomplete_recipientA | Search recipient names, UEIs, and DUNS values for use in USAspending filters. |
| usaspending_autocomplete_agencyC | Search awarding or funding agency offices for USAspending AdvancedFilterObject agency filters. |
| usaspending_search_awardsA | Search prime awards or subawards with USAspending AdvancedFilterObject filters and selected fields. Use for questions like top awards for a recipient, agency, date range, award type, NAICS, PSC, or keyword. |
| usaspending_spending_by_categoryB | Aggregate obligations/outlays by category such as awarding_agency, recipient_duns, naics, psc, federal_account, state_territory, cfda, or defc. |
| usaspending_spending_by_geographyA | Aggregate spending by state, county, congressional district, or country using place of performance or recipient location. |
| usaspending_spending_over_timeC | Aggregate obligations and outlays over fiscal years, calendar years, quarters, or months for a USAspending filter set. |
| usaspending_new_awards_over_timeA | Count new awards for a specific USAspending recipient over fiscal years, quarters, or months. Requires a recipient_id hash such as values returned by /api/v2/recipient/duns/. |
| usaspending_search_transactionsA | Search individual transaction records with USAspending AdvancedFilterObject filters. Use when award-level results are too aggregated and you need action dates, modifications, or transaction amounts. |
| usaspending_count_transactionsA | Count matching transaction records grouped by award category: contracts, grants, direct payments, loans, IDVs, and other. |
| usaspending_get_awardB | Get detailed USAspending award profile data by generated unique award ID or internal award database ID. |
| usaspending_call_endpointA | Call a documented read-only USAspending v2 endpoint that is not covered by a purpose-built tool. Blocks download and bulk_download paths. Use only with official /api/v2/ endpoints. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct operation on USAspending data, from autocomplete to searching, counting, and aggregation. No two tools have overlapping purposes, ensuring clear selection by an agent.
All tools follow a consistent 'usaspending_verb_noun' pattern with snake_case, making it predictable which action and resource a tool handles.
With 12 tools covering core operations on federal spending data, the count is well-scoped. Each tool serves a clear purpose without unnecessary redundancy.
The tool set covers all major aspects of USAspending: autocomplete, search, count, aggregation, and listing, plus a generic endpoint caller for edge cases. There are no obvious gaps for common queries.