- Home
- Skills
- APIs & Backend
- US Government Data
US Government Data
Query SAM.gov contracts, USAspending awards, Grants.gov funding and Congress trades through one API
Free
Works with the AI Agents you already use
US Government Data
Example session with this skill installed
Find open DoD solicitations for drone work set aside for small business, and tell me who has won similar contracts recently.
- Read your context and instructions
- Compiled the us government data
Summary
Searched SAM.gov for open solicitations, then USAspending for comparable awards.
get_opportunities(naics="336411", ptype="o", set_aside="SBA")
get_awards(keyword="drone", agency="Department of Defense", sort="amount")
| Source | Returned |
|---|---|
| SAM.gov | 5 open solicitations, nearest response deadline 2026-10-20 |
| USAspending | 42 related awards in the last year, 18 distinct recipients |
Read
The open set is small and the award history is concentrated — the top three recipients hold roughly 60% of the value, so this is an incumbent-heavy field.
Next steps
- Pull the full solicitation detail for the 20 October deadline
- Rank the 18 recipients by award value to find a teaming partner rather than bidding alone
Connects securely to your tools. The creator never sees your data.
About this skill
Five US federal data sources behind one key and one JSON schema, so your agent makes one integration instead of four.
What it does
get_opportunities— open federal contract opportunities from SAM.gov, filtered by NAICS, set-aside, state or procurement typeget_awards— federal awards from USAspending: contracts, grants, loans and direct payments, by agency, recipient or keywordget_grants— Grants.gov funding opportunities, by agency, category or Assistance Listing (CFDA) numberget_congress/get_congress_ticker— US House STOCK Act stock trades, overall or for one ticker
Why it exists
All of this data is free and public. Each source also ships its own friction. SAM.gov takes ncode where you would expect naics and silently ignores unknown filters, so a filtered query returns a clean-looking unfiltered result; its dates are MM/dd/yyyy rather than ISO, and the posted window caps at a year. USAspending reports no further pages at record 10,000 while real rows continue to 50,000, so a client trusting that flag truncates without an error. This skill absorbs all of it and returns one shape.
Limits, stated plainly
- Federal only. No state or local (SLED) procurement.
- Congressional trades are US House only, lag up to 45 days by law, and report dollar ranges rather than exact amounts.
- USAspending search does not reach before 2007-10-01.
- Freshness follows each government source's own cadence; nothing is held or restated.
Pure Python standard library, no dependencies. The API key is read from an environment variable and the base URL is hardcoded, so the key never reaches any other host.
US Federal data only. No state/local coverage. US House trades only (no Senate). Trade disclosures lag by up to 45 days. Amounts are reported in ranges.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts