govauctions.app

Reviewed 1h ago. Tool definitions changed on Oct 11, 2026.

• tools: 9 tools scanned
• metadata: scanned

• mediumReviewRemote tools take credentials as input

  Whatever an agent passes to a remote tool leaves the machine. Never send connection strings, tokens or passwords to a third-party MCP server unless it is the service those credentials belong to.

  get_sold_comps
• mediumReviewTool definitions changed after an earlier review

  A server that changes its tool descriptions after being approved ("rug pull") can slip new instructions to agents. Re-check what changed before trusting it.

  changed 2026-10-11

Tools (9)

• search_listings

  Search live GSA federal-surplus auction listings (facts only — no images). Filter by state, category, keyword, price, or distance from a US ZIP code. Works signed out (up to 25 rows per page). Raw listings cover sanctioned federal sources; sold-price comps span the full market.

• get_listing

  Get one live GSA listing by its id (facts only). Works signed out.

• get_sold_comps

  Sold-price comps for a described item, computed across the full government-surplus market in any market listed in `country`. Signed out: coverage (how many comparable sales, confidence, a coarse price band) plus `categoryStats`, the 25th/median/75th percentile of every sale in the item's category (in `state` when it has enough sales). Signed in or with an API key: the 25th/median/75th percentile for this item itself. `liveListingsUrl` links to the live auctions for the same item. A miss says which kind it is: reason `insufficient_comps` (too few comparable sales yet) is worth retrying, reason `category_not_priceable` (real-estate) never is — that category cannot be priced from a title. A catch-all `category` such as `miscellaneous` is not refused: it is dropped and the item is priced on its title alone, with `requestedCategory` and `categoryDropped` echoed back — check the resolved `category` and `confidence` before trusting the range.

• get_sold_comps_batch

  get_sold_comps for a list of items in one call. Each query is either a string ('2015 Ford F-150') or an object with its own q/category/country/state. Each item costs one valuation lookup, exactly as if sent alone; an item that comes back without a range is not charged. If the monthly allowance runs out part-way, the items already priced are returned and `batch.truncated` names the rest. Batch size is capped by plan (10 on the free allowance).

• get_flip_score

  GovAuctions Flip Score resale signal for one live lot, from any source, in any market with sold-price comps (valued against that market's comp archive): estimated value, effective bid, discount, and the link to the lot on its source site. Pass the lot id as it appears in a govauctions.app lot URL.

• get_sold_history

  The individual archived sales behind an item: title, final price, sale month and state, plus the range they produce. Use when you want the evidence rather than just the number. Query-anchored — describe an item; there is no way to list the archive.

• get_price_trend

  Month-by-month median sale price for an item, plus the first-to-last change — 'is this category softening?'. Computed from the same comps as get_sold_comps, so it never contradicts that range. Returns an empty series when too few months clear the sample threshold.

• get_comp_coverage

  How much sold-price data we hold per category for a market, and which categories can never be priced. Check this before building on the comps tools — it is the honest answer about what we cannot do.

• get_api_usage

  This key's usage for the current month: total calls and the separate valuation allowance (which comps, sold history, trend and flip-score draw down), plus the reset date. Call it to pace a long run instead of hitting a 429 mid-task.