No user-submitted related servers found.
Scored across 53 tools
Every tool maps to a distinct resource and access pattern, with search/detail pairs and explicit cross-references that separate near neighbors (e.g. search_companies vs search_entities, search_awards vs search_contracts, get_wage_rates vs get_wage_rate_summary). An agent should be able to pick the correct tool even within dense clusters like the NAICS and wage-determination families.
The API overwhelmingly follows snake_case verb_noun naming with search_* for discovery and get_* for detail, which makes the surface predictable. Minor deviations such as recent_changes, get_wds_by_location, and get_entities_expiring break the pattern slightly but do not cause confusion.
53 tools is heavy for a single MCP server, but the domain is genuinely broad: opportunities, contracts, vehicles, subawards, companies, entities, NAICS market intelligence, wage determinations, protests, and organizations. Each tool earns its place and the set is not padded, though the count is large enough to be a navigation burden for an agent.
The surface covers the full read-only lifecycle for the domain: search and detail paths exist for every major entity, and returned identifiers (notice_id, piid, uei, naics_code, organization_id, solicitation_number) chain cleanly into downstream tools. There are no obvious dead ends that would strand an agent mid-workflow.