Skip to main content
Glama

Egonex

Search Egonex listings

search_offers
Read-only

Search listings on Egonex, a marketplace where individual people sell things and services directly. Use it when your user wants to buy, hire, book, rent or commission something from a person rather than a store, for example:

  • items, new or used: cameras and lenses, phones, laptops, bikes, furniture, clothing, collectibles, instruments, gear;

  • lessons and coaching: languages, music, tutoring and test prep, fitness, cooking, art, coding;

  • services in person: photography, repairs (bikes, electronics, film cameras), cleaning, moving help, pet care, babysitting, beauty, tours;

  • online and freelance work: design, writing and editing, translation, software, marketing, consulting, video editing;

  • digital goods, tickets, handmade and custom work. Each result is one listing with a price and unit (per item, package, hour, session, day, week, month, night, person or project; USD), how it is delivered (in person in a city, online, or either), for physical items its condition (new, like_new, good, fair, for_parts), brand / model / gtin when the seller gave them, and ships = true when the seller posts it (your user enters the shipping address when paying on Egonex, or you pass it to pay_order when you pay), delivery_days when the seller states a usual delivery time (days to ship for posted items), up to 4 photo URLs, the listing's own page, ask_url / order_url links a person can open, and the seller: their public page, seller.answers_questions (true = ask_seller gets an answer right away), seller.trusted (true = Egonex's Trusted badge, given automatically for the seller's recent trading on Egonex, not set by the seller) and, when there are 3 or more, seller.orders_completed; seller.review_count, seller.positive_count and seller.negative_count appear when the seller has counted buyer reviews (each review is positive or negative), and seller.positive_rate (0 to 100, rounded down) once there are 10 or more. Results are ranked by how well they match the query words (rarer words count more; listings that match only common words are left out); among results that match equally well (and are equally close, for in-person services), sellers with more positive and fewer negative counted buyer reviews come first, and sellers with no reviews sit in the middle; each result's relevance says whether the listing itself (its title and description, not the store's name or intro) matches all or only some words, and matched_words / missing_words say which. Online, remote and in person in query never bring in a listing by themselves: among equally good matches, listings whose title says it come first, then those delivered that way; a listing that is neither counts as some. Only the first 12 search words of query are used (filler words like for, near or cheap don't count, nor do single letters or two-letter words in lowercase: write abbreviations in capitals, such as QA or IT); the rest come back in unused_words. When nothing matches, the response says so and lists the categories that have listings; a search within a category or a store returns that category's or store's other listings instead, marked other_filters. query can be in any language. When it isn't English, Egonex also searches an English translation of it; when it has words too short to search, ends with a place (and city is empty) or matches nothing, Egonex searches a rewrite instead. searched_as says what was searched. Put the place in city, not in query (listing cities are not matched against query words): in-person listings in that city come first, then those nearby (same metro area or within about 30 miles), and add the state when several places share the name (Portland, OR). Online, either-way and shipped listings are always included, and in-person listings without a city that don't ship come back with city_unknown = true (ask the seller before suggesting one to someone far away). Use store to list one seller's storefront. Each listing has availability (in_stock; sold-out listings are left out of results) and stock_left when only 1 to 3 are left. When you suggest a listing to your user, give them its url (the listing's own page) so they can open it. No account or API key is needed.

Input Schema

NameRequiredDescriptionDefault
cityNoCity for in-person listings, e.g. "San Francisco" or "Portland, OR". In-person listings in that city come first, then those nearby (same metro area or within about 30 miles); listings done only in person elsewhere are left out. Add the state when several places share the name. In-person listings without a city are kept and marked city_unknown (unless they ship); online, either-way and shipped listings are always included and rank after local ones.
limitNo
queryNoWhat your user wants, in a few words, e.g. "spanish lessons for kids", "used fujifilm camera", "logo design", "road bike tune-up". Matched as whole words and their word forms (lesson / lessons, colorized / colorization) against listing titles and descriptions; a word naming a category (pets, electronics, fashion, clothing, jewelry, makeup, furniture, toys, baby, camping, hobbies, crafts, books, food, tickets, rentals, templates, video, or the same in Chinese, Japanese or Korean) also matches listings in that category. Store names, intros and listing cities are not matched (put places in city). Rarer words count more, and listings that match only common words are left out. Online, remote and in person never bring in a listing by themselves: among equally good matches, listings whose title says it come first, then those delivered that way (either-way listings count as both). To keep only one kind use delivery, which is exact: delivery=remote leaves out either-way listings. Only the first 12 search words are used, so put the most important first. Write abbreviations in capitals (QA, PR, IT).
storeNoOnly this seller's storefront (the store name after shop.egonex.ai/@).
offsetNo
categoryNoOne category. Goods: electronics (electronics & accessories), fashion (clothing & shoes), jewelry (jewelry, bags & accessories), beauty (beauty & personal care), home (home & living), toys (toys & games), baby (baby & maternity), sports (sports & outdoor gear), hobbies (collectibles & hobbies), art (art, handmade & craft supplies), pets (pet supplies), books (books, music & movies), food (food & drinks). Services: lessons (lessons & tutoring), local (local services: repairs, cleaning, moving, pet care, babysitting, beauty, photography), creative (design, writing, translation, video, music), professional (software, AI setup, marketing, legal, accounting). digital (templates, e-books, courses, apps, AI agent skills, media files), rentals (tickets & vouchers), other.
deliveryNoonsite = in person only, remote = online only, hybrid = either.
conditionNoPhysical items: the lowest condition your user accepts (new > like_new > good > fair > for_parts); like_new returns new and like_new. Listings that don't state a condition are included.
max_priceNoHighest price in USD (per the listing's unit).
min_priceNoLowest price in USD (per the listing's unit).

Output Schema

NameRequiredDescriptionDefault
noteNoHow the results were found, when not every word matched or nothing did, or not every word was used.
totalYesHow many listings match in all.
offersYesListings on this page.
browse_urlNoWhen nothing matched: the sellers directory for people.
categoriesNoWhen nothing matched: categories that have listings.
next_offsetYesPass as offset for the next page; null = no more.
searched_asNoOnly when Egonex searched a rewrite of query (it isn't in English, has words too short to search, ends with a place, or nothing matched): what was searched. matched_words and missing_words are in the words of the search that found the listing: the rewrite, or, for a query that isn't in English, the query as written.
unused_wordsNoWords of query that were not used: only the first 12 search words count. Search again with them if they matter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the read-only and non-destructive annotations, it discloses non-obvious behavior including sold-out exclusion, relevance and review-based ranking, translation and query rewriting, empty-result fallbacks, location-based inclusion, and the city_unknown caution. It also states that no account or API key is needed and clarifies that seller trust badges are assigned by Egonex rather than sellers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the category bullets aid scanning, but the definition then becomes an extremely long, dense paragraph covering output fields, ranking rules, seller badges, and review thresholds. Much of this repeats structured fields or is unnecessary given the output schema, burying the most actionable invocation advice.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex ten-parameter search tool, the definition more than adequately covers query construction, language handling, geography, storefronts, ranking, empty results, availability, authentication, and result-recommendation practices. The rich input and output schemas cover the remaining structural details, leaving only minor workflow-routing and pagination gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema already documents most parameters and the description repeats substantial query and city guidance, it adds useful semantics such as multilingual translation, rewrite triggers, filler and short-word exclusions, unused_words, and category/store no-match behavior. The remaining additions are mostly elaboration rather than essential new parameter meaning, and limit/offset receive no explicit explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb, resource, and scope: searching Egonex listings from individuals selling goods and services. The examples make the discovery role clear and readily distinguish it from the messaging, ordering, and payment siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to use the tool when the user wants to buy, hire, book, rent, or commission something from a person, and adds guidance for storefront searches and recommending listing URLs. However, it does not clearly position the tool within the sibling workflow or state when to switch to ask_seller, request_order, or pay_order.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources