Developers
API keys aren't open yet. This page shows how they'll work; tell us if you'd like early access.
What a key reaches
Read-only data, no AI on our side, 5,000 calls a key a day (the count resets at 00:00 UTC; every reply carries X-Quota-Limit, X-Quota-Remaining and X-Quota-Reset in seconds, and Retry-After once the day's calls are used). A key never reaches your pursuit desk, saved searches or account.
POST /planGET /codesGET /search/suggestGET /opportunitiesGET /recompetesGET /awardedGET /forecastsGET /few-biddersGET /award-sizeGET /award-size/GET /programGET /sbirGET /sbir/companyGET /rulesGET /councilGET /directory/GET /profile/GET /registrationGET /local/GET /earmarksGET /farGET /far/POST /mcpGET /mcpDELETE /mcp
Ask with a plan
The site turns questions into a plan (a small JSON: what to measure, how to group, which filters). Send a plan and get the rows, the SQL that ran and the caveats. The plan's fields are in the catalog the MCP connector's get_catalog tool returns.
curl -s https://api.spendquery.com/plan \
-H "Authorization: Bearer sqk_your_key" \
-H "content-type: application/json" \
-d '{"intent": "aggregate", "metric": "obligations", "group_by": ["recipient"],
"fiscal_years": [2026], "filters": [{"dimension": "agency", "values": ["Department of Energy"]}],
"limit": 10}'Lists
curl -s "https://api.spendquery.com/opportunities?naics=541512&limit=20" -H "X-API-Key: sqk_your_key" curl -s "https://api.spendquery.com/recompetes?months=12&min_value=1000000" -H "X-API-Key: sqk_your_key" curl -s "https://api.spendquery.com/sbir?agency=Department+of+Energy&phase=Phase+II" -H "X-API-Key: sqk_your_key" curl -s "https://api.spendquery.com/rules?area=far&kind=proposed" -H "X-API-Key: sqk_your_key"
MCP connector for AI assistants
Add SpendQuery as a remote MCP server in Claude, ChatGPT or any MCP client: URL https://api.spendquery.com/mcp. No sign-in or key is needed (600 calls a day per network address); with an API key as a bearer token you get your key's own allowance. The assistant plans the question itself; SpendQuery runs it read-only, within a time limit, and every number comes with the SQL or the record behind it.
- Claude (claude.ai, Desktop): Customize → Connectors → Add custom connector, paste the URL. After we add tools, reconnect it so Claude sees them.
- ChatGPT: add it as a custom connector (an MCP server) in the apps and connectors settings, where your plan allows it.
- Keys: send a key as a bearer token where the client allows it. A key written into a connector's address shows up in screenshots and logs; if you do that, keep it private and make a new key if it's ever seen.
Tables and charts in the chat
In hosts that support MCP Apps (Claude, ChatGPT, VS Code), four tools answer with an interactive view instead of raw data: open notices as a table with due dates and set-asides (search_notices), a company's federal profile with its agencies and years (company_profile), contracts coming up for re-bid with the incumbent (recompetes) and spending answers as bar charts (run_plan). Links in the views open SpendQuery's pages; the host may ask you once to allow the view. Other clients get the same data as before.
Tools
- Spending:
get_catalog(what can be asked, the plan schema and examples),run_plan(run a plan: by agency, company, state, county, city, congressional district, industry, product, program, set-aside, year and more),search_codes,search_recipients,browse_codes. - Opportunities and companies, no plan needed:
search_notices(open SAM.gov notices),get_notice(one notice: fit, incumbent, deadline, what changed),company_profile,recompetes,award_prices(typical award sizes and GSA labor rates). - Getting ready to bid:
size_standard(SBA size standards),naics_finder(the codes buyers use for your work),vehicle_match(the GWACs, IDIQs and GSA Schedule carrying an industry's money),primes_and_subcontractors(who does the work as prime and as subcontractor: teaming leads). - State and local:
find_bid_portals(where a state, county or city posts its own bids: the portal, the platform it runs on, the open-bids list and where vendors register; every state, every county and the cities and towns of 10,000+) andsearch_local_bids(the state and local bids and contracts SpendQuery loads from open data). - Grants, SBIR and rules:
grant_opportunities(open and forecast on Grants.gov),sbir_awards(SBIR and STTR awards since 1983),search_farandget_far_section(the FAR and DFARS).
Prompts
Four prompts (slash commands in Claude Desktop) chain the tools the way SpendQuery's own workflows do: bid_no_bid (a go / no-go memo on one SAM.gov notice), qualified_work (open federal work a company can win, ranked, with what was left out and why), market_research(a draft FAR Part 10 market research report) and sources_sought_reply (a short reply to a sources sought or RFI, past work left as placeholders). Each asks the assistant to take every number from a tool result.
Try asking
- Open janitorial notices in Virginia, due in the next 30 days
- Show Leidos's federal profile
- Which IT contracts in Virginia are coming up for re-bid, and who holds them?
- FY2026 federal spending in each of California's congressional districts
- Federal contracts performed in Simi Valley, CA in FY2025, by company
- Where do I bid for Ventura County and the City of Ventura?
- Open janitorial notices within 20 miles of 93065
What's new
- November 6, 2026: distance search:
search_noticestakesnear(a ZIP, or a city or county) andmiles, andrun_plananearfilter ("40 miles of Los Angeles, CA") for federal money in the counties within reach.find_bid_portalsalso answers with the state's small-business certifications and free help (certification_and_help) and, for a city, a link to the open federal notices performed there. - November 5, 2026: tables and charts in Claude and ChatGPT (MCP Apps);
find_bid_portals; a city filter for spending (place of performance);search_notices,company_profile,recompetes,award_pricesand thesources_sought_replyprompt; tool results also as structured content, for clients that read it. - November 4, 2026:
grant_opportunitiesandprimes_and_subcontractors.
Fair use
The data comes from public sources (USAspending.gov, SAM.gov, SBA, the Federal Register, state and local portals); cite them and SpendQuery. Don't share keys; revoke a key you no longer use. The terms apply. Where the numbers come from.