mcp-public-award-monitor

Government Contract Award Monitor MCP Server

MCP server for the Mamba Labs Government Contract Award Monitor actor on Apify.

Pick a register and a time window. It returns the companies that won public work in that window, one flat row per winning company, with award count, total value, awarding body, award date, and a resolved company domain.

Install

npx -y @mambalabsdev/mcp-public-award-monitor

Claude Desktop

{
  "mcpServers": {
    "mamba-public-award-monitor": {
      "command": "npx",
      "args": ["-y", "@mambalabsdev/mcp-public-award-monitor"],
      "env": { "APIFY_TOKEN": "your-apify-token" }
    }
  }
}

Get an Apify token at console.apify.com/account/integrations.

Tool

monitor_public_awards

Register and window in, the companies that won public work out.

Input	Type	Required	Notes
register	enum	yes	Which award register to read. us_federal_contracts and us_federal_grants from USASpending, us_nih_sbir from NIH RePORTER, uk_contracts_finder and uk_find_a_tender from the UK registers. Default us_federal_contracts.
window_days	string	no	How many days back from today to read awards for, 1 to 90. US federal data lags about two days, so do not use a one day window on the US registers. Default 7.
min_award_value	string	no	Drops awards below this amount in the register's own currency. Set to 0 to keep everything. Default 100000.
max_entities	string	no	Hard cap on billed rows, 1 to 1000. Winners are sorted by total award value, and the run log says how many were dropped. Default 100.
exclude_government_recipients	boolean	no	Drops winners that are themselves government, universities, or public authorities. Leave this on for the grant registers or you get state departments of education instead of companies. Default true.
resolve_domains	boolean	no	Looks up each winner's website. Turning it off makes the run roughly 20x faster and returns recipient_domain as null with domain_status not_attempted. Default true.
domain_confidence_floor	enum	no	strict, standard or loose. Strict returns fewer domains and almost no wrong ones. Loose returns the most domains and about a third of them are wrong. Default standard.
max_charge_usd	number	no	Optional spending cap for this call, in USD. The actor stops before any charge that would take the run past this amount and keeps every row already charged.

Reading the output

One row per winning company, not one per award. total_award_value, largest_award_value and award_count_in_window size the opportunity. recipient_register_id is the UEI in the US and the Companies House number in the UK, which is what you match against a CRM. latest_award_url is the deep link to the source record.

Billing

You are charged per winning company returned, plus a small actor start fee. max_entities is therefore a hard cost cap.

Prices from the live pricing record, read 2026-10-16:

Event	Price per event (USD)	Fires when
apify-actor-start	$0.00005	Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).
award-winner-found	$0.005 on the Free plan, down to $0.00425 on higher Apify plans	Charged once per company returned that won a public contract or grant in your window. Summary rows carry no company and are never charged.

The current price is on the actor's Apify page. Running this server consumes Apify credits.

What this server does and does not do

It is a thin client for the Apify actor. It passes your input through and returns the actor's output unchanged. Every behavior described above lives in the actor, not here.

This is not a tender feed and not a procurement pipeline tool. It does not tell you what is open to bid on. It reports awards that have already been made and names the company that won.

Errors are surfaced, never swallowed. An invalid input, an invalid token, an exhausted balance, a timeout, or a run that returns anything other than a dataset all come back as an explicit tool error rather than as an empty result.

Source

The actor is on the Apify Store. This wrapper is MIT licensed.

Built by Mamba Labs