Gao Protests MCP server

@pipeworx/gao-protests

GAO bid-protest decisions — government-contract award disputes ruled on by the US Government Accountability Office ("did anyone protest this award", "how often does this agency lose protests"). Pairs with usaspending and dod-contract-announcements, which cover the award side but not disputes.

Part of Pipeworx — an MCP gateway connecting AI agents to 1576+ live data sources.

Tools

• gaoprotestsrecent(days?, outcome?, limit?) — recently decided protests, optionally filtered by outcome (denied|dismissed|sustained).
• gaoprotest(bnumber) — a single decision by B-number, with the decision PDF link.
• gaoprotestssearch(protester, limit?) — search accumulated decisions by protester/company name.
• gaoprotestscoverage() — total decisions held, earliest/most-recent decided_on, last crawl time.

Auth

Keyless — no operator key needed. Backed by gaobidprotests, refreshed daily by workers/data-pipeline (dataset gao-protests).

Data sources

page. It embeds a Drupal Views "recent decisions" block directly in the page HTML (no JS challenge), showing the ~5 most-recent decisions.

• — the bid-protests landing

once per new B-number for its exact decided date and PDF link.

• — each decision's own page, fetched

Coverage is a rolling accumulation, not GAO's full protest archive. The filtered search endpoint (gao.gov/search?f[0]=ctypesearch:Bid Protest Decision) sits behind an Akamai Bot Manager proof-of-work JS interstitial that cannot be solved from a server — full Chrome headers over HTTP/2 don't help, this is a JS-execution challenge, not a header fingerprint. The landing page's own "More" link points at that same blocked endpoint, and there is no other reachable pagination. So this pack can only ever see the decisions GAO has published since it started crawling — gaoprotestsrecent/search answer against what has accumulated in gaobidprotests so far, not against GAO's complete decision history. gaoprotestscoverage reports exactly how far back that goes.

Both hosts need the full Chrome header set (User-Agent, Accept, Accept-Language, sec-ch-ua, Sec-Fetch-, Upgrade-Insecure-Requests over HTTP/2) — a plain User-Agent alone gets a 403. This is a header-fingerprint block, not a Cloudflare-egress block; no proxy is needed.

The protested AGENCY is not available. It appears only inside each decision's PDF text, never in the page HTML, and this pipeline has no PDF text extraction. Rather than guess an agency from context (or from the protester's history), the field is omitted entirely — presenting a guessed agency as fact would be worse than not having it.

A decision can carry several B-numbers (e.g. B-424484,B-424484.2 for an original protest plus a reconsideration). The table's primary key is the first number in that string; gao_protest also matches a non-primary number (like the .2 suffix) by searching the raw string.

Outcome is prose, not an enum ("We deny the protest.", "We dismiss the request for reconsideration.", "We sustain the protest."). It's normalized to denied | dismissed | sustained | other for filtering, and the raw sentence is always kept alongside it.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "gao-protests": {
      "url": "https://gateway.pipeworx.io/gao-protests/mcp"
    }
  }
}

What this endpoint actually serves

Shortened. The full README is on GitHub.