Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@US Federal Procurement MCP find open HUBZone contracts in Maryland under $250,000"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Federal contracting intelligence for small businesses — as an MCP server. Search contract opportunities, understand set-asides and NAICS codes, and analyze solicitations for small-business fit and risk — from inside Claude, Cursor, or any MCP client.
This fills the biggest gap in US small-business (SBA) contracting: an LLM trained on the public internet cannot know current contract opportunities or reliably recall the set-aside rules, FAR thresholds, and NAICS structure that determine whether a bid is even worth pursuing. This server makes that real and queryable.
Tool | What it does |
| Search federal opportunities by keyword / agency / set-aside / NAICS / state / value / deadline |
| Set-aside, sector, agency & value overview + urgent deadlines |
| Evidence-backed small-business fit assessment (insufficient / mismatch / review / potential) + red-flag scan (bonds, turnover, past-performance) |
| Phase-3 deep review: fetches full notice + attachments, combines a bidder capability profile with source-linked extraction (instructions, evaluation factors, clauses, amendments) |
| Translate a description into NAICS sectors |
| Explain a set-aside (Small Business, 8(a), HUBZone, WOSB, SDVOSBC…) |
| Micro-purchase, SAT, Miller Act bond, subcontracting-plan thresholds |
| Full record (incl. POC, links, award) + state name for one opportunity — live or sample |
| What a SAM.gov type code means (sources sought, solicitation, J&A…) |
Everything is deterministic, typed, and honest about its data source.
Related MCP server: GovCon
python3 -m venv .venv
.venv/bin/pip install -e ".[test]"
.venv/bin/pytest tests/ -q # 84 tests incl. real MCP stdio integration
.venv/bin/us-gov-mcp # or: .venv/bin/python -m usgovmcp.serverClaude Desktop / Claude Code / Cursor → see configs/mcp-config.json
(canonical example: same JSON works for Claude Desktop and Cursor; for Claude Code,
use claude mcp add). Set PYTHONPATH to this repo; optionally add a SAM_GOV_API_KEY.
Default: a bundled set of clearly-labeled sample opportunities so it works and is tested with no key.
Live (SAM.gov): get a free public API key from your SAM.gov account → Account Details → request a public API key. Set SAM_GOV_API_KEY. The provider (SAMGovProvider) already talks to api.sam.gov/opportunities/v2/search and is unit-tested against the real response shape. Live data is never faked — until a key is set, labeled samples are returned.
us-gov-mcp/
├── usgovmcp/
│ ├── server.py ← FastMCP server wiring all tools
│ ├── knowledge.py ← NAICS, set-asides, FAR thresholds, red-flag rules
│ ├── analyzer.py ← evidence-backed fit assessment + red-flag scan
│ ├── solicit.py ← bidder capability profile + source-linked extraction (Phase 3)
│ ├── providers.py ← bundled + SAM.gov live providers
│ ├── models.py ← typed Opportunity / search params / ProviderResult
│ ├── intel.py ← market-snapshot aggregation
│ └── sample_data.py ← labeled demo opportunities
├── configs/
├── scripts/smoke.py ← CI startup check (fails pipeline on broken server)
├── scripts/secret_scan.sh ← CI gate: blocks committed credentials
├── cache.py ← bounded TTL cache (protects SAM.gov quota)
├── tests/ ← 84 tests incl. real stdio protocol integration
├── constraints.txt ← tested/locked dependency set for releases
├── CONTRIBUTING.md SECURITY.md LICENSE CHANGELOG.md
├── pyproject.toml ← also ruff + mypy config
└── README.mdCI runs two jobs: test (Python 3.10/3.11/3.12) and quality (ruff
lint + format check, mypy, package build, secret scan).
MIT licensed. Not legal advice — always read the full solicitation before bidding.
analyze_solicitation never produces a confident fit from missing evidence:
unknown notices and empty text return insufficient_information.
Provider results are typed (ProviderResult): ok, no_matches,
authentication_error, rate_limited, upstream_error, parse_error,
no_key. Asking for sam_gov without a key returns no_key — never a silent,
misleading empty list.
All data is honestly labeled by source (bundled_sample vs sam_gov).
Evidence-backed small-business fit assessment + red-flag scan.
Provide either a notice_id (looked up from live SAM.gov or the sample
pool) or pasted text of a solicitation. Returns one of:
insufficient_information / likely_mismatch / requires_capability_review /
potential_fit, with the evidence reviewed, gates, and what's missing.
Effortless proof rule: missing evidence can NEVER produce a confident fit.
Inputs: text, source, notice_id, set_aside, +3 more.
Return federal procurement thresholds (USD) with source provenance (citation, effective date, superseded value). Names: micro_purchase_general, simplified_acquisition_threshold, miller_act_bond, subcontracting_plan_services, subcontracting_plan_construction.
Inputs: name.
Map a goods/services description to NAICS sectors (note: curated 2-digit sectors).
Inputs: query.
Explain a SAM.gov set-aside (official codes: SBA, SBP, 8A, 8AN, HZC, HZS, WOSB, WOSBSS, EDWOSB, EDWOSBSS, SDVOSBC, SDVOSBS, VSA ...).
Inputs: code_or_label (required).
Overview of available federal opportunities: set-asides, NAICS sectors, agencies, typical values, and urgent deadlines.
Inputs: state, set_aside, max_results.
Full structured record for one opportunity by notice id (live SAM.gov if available, else sample pool). Sensitive/noisy fields are behind detail=true.
Inputs: notice_id (required), source.
Explain a SAM.gov opportunity type (ptype) code. Official: o=Solicitation, k=Combined Synopsis/Solicitation, r=Sources Sought, p=Presolicitation, u=J&A, a=Award, s=Special Notice, g=Surplus, i=Intent to Bundle.
Inputs: code (required).
Search federal contract opportunities (beta.SAM.gov).
Filters: free-text query, agency, set-aside (small/8a/hubzone/wosb/sdvosb), NAICS (sector or 2-6 digit code), performance state (2-letter), opportunity type code, value range (USD), and response-deadline window. Returns typed results distinguishing no-match from an upstream failure.
Inputs: limit, naics, query, state, +7 more. Returns: Structured, typed provider result (audit P0-5).
Phase-3 evidence-backed solicitation review.
Looks up the notice (live SAM.gov by notice id, else sample), fetches the full description and attachment metadata (bounded, content-type checked), then combines BIDDER CAPABILITY facts with source-linked extraction of submission instructions, evaluation factors, mandatory clauses, period/place, and amendment history.
Missing bidder facts or missing documents surface as findings — a gap can never inflate the result toward 'potential_fit'.
Inputs: notice_id (required), source, capabilities, certifications, +7 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 9 tools
Most tools have distinct purposes: search vs details vs analysis vs reference lookups are clearly separated. However, analyze_solicitation and solicitation_review overlap in solicitation-focused assessment, and market_snapshot_tool could be confused with search_opportunities by agents looking for an overview.
Most tools use verb_noun patterns like search_opportunities, look_up_naics, analyze_solicitation, and federal_thresholds. This is inconsistent with market_snapshot_tool and opportunity_details, which use noun_phrase naming, and the mix of 'look_up' vs 'lookup' style is not fully predictable.
Nine tools is a well-scoped size for a federal procurement domain, covering search, reference, and analysis workflows without bloat. Each tool serves a distinct functional area, and the count feels neither thin nor overwhelming.
The server covers core workflows: searching opportunities, viewing details, understanding codes/classifications, and analyzing solicitation fit. Minor gaps exist, such as no direct tool for listing agencies or saving/tracking opportunities, but the main user journey is supported end-to-end.
MCP access to the U.S. federal procurement graph: contracts, opportunities, entities, and more.
Federal+SLED govcon MCP: SAM, USASpending, recompete, hearings, policy intel, search. Private AI.
Federal contract research and approved pursuit workflows. Paid FedFinder account and OAuth required.
Search U.S. federal contract opportunities (RFPs, bids, awards) from SAM.gov official data.
