Real Poshmark sold prices for secondhand clothing, shoes and bags. Ask what an item sells for, by condition, or whether it’s worth buying at a price to resell.
Scored across 3 tools
buy_or_pass is essentially a decision wrapper around sold_comps, so the two overlap substantially, though the descriptions make clear one returns a verdict and the other raw comp data. value_donation_list is clearly distinct, targeting bulk list valuation rather than a single item. Only the buy_or_pass / sold_comps boundary could occasionally confuse an agent.
Names mix conventions: buy_or_pass is verb_verb, sold_comps is a bare noun phrase, and value_donation_list is verb_noun. Each is readable and self-explanatory, but there is no predictable pattern an agent could generalize from.
Three tools is lean but each covers a genuinely different workflow (single-item verdict, single-item comps, bulk donation valuation) with no filler. It sits at the modest end of the ideal 3-15 range and would benefit from a couple more entry points, but nothing is bloated.
The set covers the core lifecycle of resale pricing: research comps, decide to buy, and value a list. Gaps remain — no bulk buy/pass evaluation (explicitly one item at a time) and no view of active listings or fee breakdowns — but these are workable around via repeated calls to the existing tools.
Whether an item is worth buying at a given cost to resell on Poshmark: buy, maybe or pass with the reason, judged from its clean sold comps after Poshmark's fee. Call it for one item at a time; if it reports busy, wait the given number of seconds and call again.
query: brand + item, e.g. "patagonia better sweater".
cost: what you'd pay, e.g. the thrift-store tag price, in the same currency as source (USD for poshmark, CAD for poshmark_ca).
min_profit: smallest profit after fees worth the effort (default 10).
size / condition: same filters as sold_comps.
source: "poshmark" (US, default) or "poshmark_ca" (Poshmark Canada; prices and fees in CAD).
Inputs: cost (required), query (required), size, source, +2 more.
What an item actually sold for on Poshmark: median sold price, typical range (p10-p90), days to sell, what the seller keeps after fees, price by condition, a confidence rating, and the matching sales. Call it for one item at a time; if it reports busy, wait the given number of seconds and call again.
query: brand + item, e.g. "coach tabby 26" or "lululemon align leggings", or a plain item type like
"womens jeans". For kids' clothing put girls, boys, kids, toddler or youth in the query ("girls jeans");
otherwise kids' sizes are removed.
size: only this size, e.g. "8", "M" or "10.5". Leave it out unless the user named a size: it can leave
very few sales.
condition: "new", "used", a plain word (nwt, like new, excellent, very good, good, fair, poor), or an
exact grade: new_with_tags, not_new_with_tags, used_like_new,
used_excellent, used_good, used_fair (comma-separated for several).
days: only sales from the last N days (1-365). Poshmark lists sold results by relevance, not date, so
without it the sales can be years old; days=365 (or 90) keeps prices recent.
limit: how many individual sales to include in `sales` (default 10, 0-50). Each sale has the same fields
as a /v1/sold item.
exclude_seller: comma-separated seller usernames to leave out (case-insensitive).
sort: order of the included sales: "recent" (newest first), "price_asc" or "price_desc". Stats are unaffected.
department: comma-separated: Women, Men, Kids, Home, Pets, Electronics. "Kids" also keeps kids' sizes, and
adds "kids" to a query with no kids' word ("snow pants" searches "kids snow pants"; query_note says so).
category: comma-separated Poshmark categories, e.g. "Jeans".
kids_age: only kids' sales in "baby" (0-24 months), "toddler" (2T-5T) or "big_kids" (4/5 and up) sizes.
Kids' searches otherwise keep 12-24 month and toddler sizes, as Poshmark's Kids department does.
include_removed: true also returns removed_items, the sales cleaning dropped, each with a removed_reason.
deep: true reads up to ~190 sales (4 pages of up to 48, in Poshmark's relevance order) instead of one
page (slower when not cached, about 10s; one lookup).
source: "poshmark" (US, default) or "poshmark_ca" (Poshmark Canada; prices and fees in CAD).
Inputs: query (required), days, deep, size, +9 more.
Fair-market values for a whole donation list (clothing, shoes, bags and household goods: kitchen, home, electronics, media, toys, baby gear, pets, beauty), each item with the Poshmark sales behind it, a list total and a dated method paragraph the donor can keep with their records. One call values up to 100 items and costs one lookup per item. Call it once with the whole list, not once per item.
items: a list of objects, one per item. Only description is required.
description: what it is, as the donor would say it: "womens handbag", "mens suit", "kids snow pants",
"Levi's 501 jeans", "KitchenAid stand mixer". Put brand and model in brand or description. Goods are
valued only from sales of the same product, so name it as it would be listed; a count in the text
("throw pillows (4)") is read as the quantity.
brand: optional, e.g. "Coach". With a brand the item is priced from that brand's own sales when enough are
saved, else from its category.
condition: optional. new_with_tags, used_like_new, used_excellent, used_good, used_fair, a plain word
(like new, good, fair), or new or used. Default used, which is right for most donations.
category, department, size: optional; read from the description when left out. A kids' size such as
"4T" marks the item as kids'.
kids_age: optional, for kids' items: "baby" (0-24 months), "toddler" (2T-5T) or "big_kids" (4/5 and up).
quantity: optional, default 1. total is value times quantity.
source: "poshmark" (US, USD, default) or "poshmark_ca" (Poshmark Canada, CAD).
examples_per_item: how many of the sales behind each value to include (0-5, default 2). Each has a title,
price, sold date and link.
days: only sales from the last N days (1-3650); 365 is the last 12 months. Default: every sale.
sold_after, sold_before: only sales sold on or after / on or before these dates (YYYY-MM-DD).
On the Free, pass and Starter plans every value uses only sales from the last 90 days (any window is cut to
it, history_days is 90 and history_note says so), except keys issued before Oct 25 2026, which keep the full
archive (history_days is null); Growth and Scale use the full archive, back to 2012.
Each item gets value (the median sold price), low and high (the 25th and 75th percentiles), p10 and p90
(the 10th and 90th), sales_used, oldest_sold and newest_sold (within the window), matched_on ("brand +
item", "item description", "category + department" or "category, all departments"), broadened (true when
the value comes from wider sales than the item as described: no brand match, a description reduced to its
category, all departments, or the condition group instead of the exact grade), condition_matched (the grade
or group the sales are in), by_condition (median and range per grade), a confidence rating and a reason
that says why. basis is the older name of matched_on. An item with nothing to go on has value null and a
reason; never guess a value for it. The list has total, items_valued, method and disclaimer. This is resale
market data, not tax or legal advice; appraisal_may_be_needed is true when a single item, or a group of similar items (same category), is over $5,000.
Inputs: items (required), days, source, sold_after, +2 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Add one secure layer between your agents and this server.