Capture MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TANGO_API_KEY | No | API key for Tango API. Enables Tango tools (5 additional tools). Optional. | |
| SAM_GOV_API_KEY | No | API key for SAM.gov. Enables SAM.gov and Join tools (6 additional tools). Optional. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lookup_reference_codeA | Look up the official FPDS description for a procurement reference code, or list a whole domain. Domains: set_aside, extent_competed, award_type, solicitation_procedure, competition. Use this BEFORE filtering or reporting on any code — e.g. set_aside 8A is '8(a) Competed' while 8AN is '8(a) Sole Source'. Static lookup: no API key, no network. |
| get_usaspending_awardsB | Get federal awards data for a specific agency and fiscal year. Returns award counts, obligations, and top awards. |
| get_usaspending_spending_by_categoryB | Get spending breakdown by award category (contracts, grants, loans, etc.) for an agency and fiscal year. |
| get_usaspending_budgetary_resourcesA | Get budgetary resources and obligations for an agency in a fiscal year. |
| search_usaspending_awards_by_recipientB | Search for federal awards by recipient name, with optional filters for time period and amount ranges. Great for investigating specific companies or organizations. |
| get_award_detailA | Get the full FPDS record for a single procurement award from USASpending — the verification primitive: type_set_aside with description, extent_competed, number_of_offers_received, other_than_full_and_open competition authority, and current vs ultimate completion dates. Use it to confirm that a filtered search actually returned what it claimed before a number goes in a memo. Accepts a procurement generated award ID (CONT_AWD_... or CONT_IDV_...) or a bare PIID (resolved via award search first). Assistance IDs (ASST_...) are rejected because they do not carry FPDS competition fields. |
| aggregate_contractsA | Aggregate federal contract awards from USASpending without pulling rows: group by awarding_agency, awarding_subagency, recipient, naics, psc, month, or set_aside, with metric 'obligations' (dollars) or 'count' (prime awards). This is the tool for questions like 'how many 8(a) sole source awards per agency in Aug-Sep 2025'. Counts state their unit and the date filter states its date_type. group_by=set_aside issues one upstream query per code (~4s each due to rate pacing); metric 'count' is supported for group_by set_aside only (USASpending exposes counts per filter, not per category). |
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 7 tools
Most tools map to clearly different operations—reference lookup, recipient search, award detail, aggregation, and budget summaries. However, get_usaspending_awards, get_usaspending_spending_by_category, and get_usaspending_budgetary_resources are similarly named summary endpoints, and get_usaspending_awards overlaps somewhat with aggregate_contracts in producing counts and obligations.
All names are snake_case and action-oriented, so the general pattern is readable. There is a minor inconsistency: get_usaspending_* and search_usaspending_* use a domain prefix, while get_award_detail, aggregate_contracts, and lookup_reference_code omit it.
Seven tools is a well-scoped size for this server's purpose. Each tool addresses a distinct querying, lookup, or aggregation need without padding or unnecessary duplication.
The server covers award summaries, spending categories, budgetary resources, recipient search, award detail verification, reference code lookups, and flexible contract aggregation. Minor gaps include no assistance-award detail endpoint and no general award search by arbitrary fields, but the core workflows are well supported.