Skip to main content
Glama

marketua

An MCP server that lets AI agents (Claude Desktop, Hermes Agent, Cursor, OpenCode, …) search Ukrainian marketplaces — OLX, Hotline.ua, Prom.ua and Rozetka — from a plain-language prompt and get back structured offers with links.

Status: alpha. OLX, Hotline and Prom work out of the box (no tokens); Rozetka is covered through the optional Bright Data MCP server (free tier: 5 000 requests/month). Verified with MCP Inspector and a real agent (OpenCode), including a 4-marketplace price comparison from a single prompt.

Idea

Ask in natural language:

"SSD 120–560 GB, 2.5", used, up to 1500 UAH"

and get a structured list of matching offers — title, price, location, link — instead of a wall of search results.

Related MCP server: shopping-radar

Built-in web search

This MCP server

Structured filters (price, form factor, condition)

guesswork

exact API filters

Uniform, comparable result list

no

yes

Repeatable / schedulable queries

no

yes

Fresh marketplace listings

often stale

live

For one-off lookups the difference is small; for structured comparison and monitoring it is the point.

How it works

natural-language prompt
        │
        ▼
  LLM (OpenCode / Hermes / Claude)  ── maps prompt → tool arguments
        │
        ▼
  MCP tools  ── search, filters, details, references
        │
        ▼
  Marketplace providers ── OLX (JSON API), Hotline / Prom (SSR), Rozetka (Bright Data MCP)
        │
        ▼
  structured offers (title, price, location, url)

Tools

The server exposes these MCP tools (OLX / Hotline / Prom — registered out of the box):

  • search_offers(query, min_price, max_price, region_id, city_id, category_id, state, filters, limit, offset, include_promoted, sort) — one page of offers plus the total match count. Category-specific attributes go into filters as {"key": "value"} (choice) or {"key": [from, to]} (range). sort: newest (server-side), price_asc/price_desc (sorts the returned page). Promoted listings are excluded unless include_promoted=True.

  • get_offer_details(offer_id) — full listing: plain-text description, characteristics, photo URLs, seller, status, dates.

  • list_filters(query, category_id) — discovers which category-specific filters exist for a query (keys + sample values). Call before search_offers when an attribute is mentioned. category_id restricts the sample to one category (broad queries otherwise mix categories).

  • list_categories() — curated category id/name list (static snapshot; OLX deprecated the live category endpoint).

  • list_regions() — OLX region (oblast) and major city ids.

  • hotline_search_offers(query, min_price, max_price, limit, offset) — Hotline product models (new items from shops) with the minimum shop price.

  • prom_search_offers(query, min_price, max_price, limit, offset) — Prom products (new items from shops).

Rozetka has no tool in this server — it is queried through the Bright Data MCP browser tools (see Optional: Bright Data MCP). The server's instructions tell the agent to do so automatically for price comparisons.

Example prompts

Find me an SSD 120–560 GB, 2.5", used, up to 1500 UAH on OLX

Cheap used monitors in Kyiv up to 2000 UAH, show the 5 cheapest

Details of offer 931436822

The agent maps these onto the tools: it calls list_filters to learn valid filter keys, list_regions/list_categories for ids, then search_offers with the narrowed arguments. Server-side instructions tell it to report only filters actually used and to format the result as a list with prices and links.

Quick start

pip install marketua        # or: uvx marketua (no install needed)
marketua                    # runs the MCP server over stdio (a client spawns it)

For development from this repo:

python3 -m venv .venv
.venv/bin/pip install -e ".[dev]"
.venv/bin/python -m pytest -q     # tests

Connect an agent

Any MCP client works. OpenCode:

// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "marketua": {
      "type": "local",
      "command": ["uvx", "marketua"],
      "enabled": true
    },
    // Rozetka (and any JS-rendered / Cloudflare-protected site) goes through
    // the Bright Data MCP — free tier: 5 000 requests/month. Token from
    // Bright Data → Settings → API Tokens (see .env.example in this repo).
    "brightdata": {
      "type": "remote",
      "url": "https://mcp.brightdata.com/mcp?token={env:BRIGHT_DATA_API_KEY}&tools=scrape_as_markdown,scrape_as_html,search_engine&groups=browser",
      "enabled": true
    }
  }
}

If the client can't find uvx: GUI apps (VS Code, Claude Desktop, Cursor) often don't inherit your shell's PATH, so a freshly installed uv (in ~/.local/bin) may be invisible to them. Find the path with which uvx and put it in command, or skip uvx entirely: pip install marketua and use marketua as the command.

Optional env vars. The server reads MARKETUA_DISABLE_PROVIDERS (comma-separated: olx, hotline, prom) from its own environment to disable marketplaces. Most MCP clients (Claude Desktop, Cursor — see below) forward a per-server env block from the config; OpenCode does not forward env to spawned local MCP servers, so for OpenCode export the variable in the shell before launching it.

Then ask e.g. "Find me a used monitor up to 2000 UAH". The model picks the right tool itself: marketua_* for OLX / Hotline / Prom (free), brightdata_* for Rozetka and other hard-to-reach sites.

Optional: Bright Data MCP (for Rozetka)

Rozetka is a Cloudflare-protected Angular SPA — it needs a real browser, so it goes through Bright Data's official MCP server. It is optional: without it the agent searches OLX / Hotline / Prom and says Rozetka was skipped; with it, price comparisons cover all four marketplaces.

  • Free tier: 5 000 requests/month, no credit card. Token: Bright Data → Settings → API Tokens (not the proxy credential). The agent spends ~2–4 requests per search (navigate + snapshot + get_text).

  • Data lives only in your chat — nothing is stored by us.

Claude Desktop (claude_desktop_config.json). The env block is optional — include it only to disable marketplaces (comma-separated: olx, hotline, prom):

{
  "mcpServers": {
    "marketua": {
      "command": "uvx",
      "args": ["marketua"],
      "env": {
        "MARKETUA_DISABLE_PROVIDERS": "prom"
      }
    },
    "brightdata": {
      "url": "https://mcp.brightdata.com/mcp?token=YOUR_TOKEN&tools=scrape_as_markdown,scrape_as_html,search_engine&groups=browser"
    }
  }
}

Cursor (~/.cursor/mcp.json) — same optional env block for disabling marketplaces:

{
  "mcpServers": {
    "marketua": {
      "command": "uvx",
      "args": ["marketua"],
      "env": {
        "MARKETUA_DISABLE_PROVIDERS": "prom"
      }
    },
    "brightdata": {
      "url": "https://mcp.brightdata.com/mcp?token=YOUR_TOKEN&tools=scrape_as_markdown,scrape_as_html,search_engine&groups=browser"
    }
  }
}

For manual verification of every tool, use MCP Inspector:

npx @modelcontextprotocol/inspector --web uvx marketua

Platforms

Marketplace

Status

Data source

Cost

OLX.ua

MVP (alpha)

public JSON API (api/v1/offers)

free

Hotline.ua

MVP (alpha)

SSR search page

free

Prom.ua

MVP (alpha)

SSR search (embedded JSON-LD)

free

Rozetka.ua

via Bright Data MCP

remote browser (JS-rendered site)

free tier: 5 000 req/mo

Architecture

One stable interface, many providers:

MCP layer (tools)  →  Provider interface  →  [OLXProvider, HotlineProvider, PromProvider]
                                         (Rozetka — via the Bright Data MCP, no provider)
  • MCP transport: stdio (simplest, the client spawns it as a child process). No hosted server — shipped as a Python package (pip install marketua / uvx marketua), so each user runs their own local instance.

  • Provider interface keeps marketplace specifics behind one abstraction, so adding a platform never touches the agent-facing layer.

  • OLX category ids are a static snapshot (the live category endpoint is deprecated); the server detects stale ids at query time and warns instead of silently returning wrong results.

  • Credentials (e.g. the Bright Data token) are configured by you in your client or shell, never committed.

License & disclaimer

MIT. This project is educational. It uses only public, unauthenticated data and respects robots.txt and rate limits. Marketplace ToS may restrict automated access — use responsibly, keep request rates low, and do not redistribute data at scale or bypass any access controls. The optional Bright Data MCP is a third-party service with its own ToS and free-tier limits.

Available Tools

7 tools
get_offer_detailsA

Get full details for one OLX offer by id: plain-text description, characteristics, photo URLs, seller, status and dates.

Inputs: offer_id (required).

hotline_search_offersA

Search Hotline.ua (Ukrainian price aggregator) and return matching product models with their price range across shops. Returns {'total', 'returned', 'offers'}; each offer has id, title, price (minimum shop price, UAH), currency, url. NOTE: Hotline returns product MODELS, not individual listings — price is a range, and location is not available in search results. Use for comparing prices/specs of a product model. For used/individual listings (with location), also call search_offers (OLX).

Inputs: query (required), limit, offset, max_price, +1 more.

list_categoriesA

List OLX categories (id + name) so you can look up a category_id to pass to search_offers. Static snapshot of the most useful categories — the live OLX category endpoint is deprecated. Omit category_id in search_offers when the category is not listed here.

Inputs: no named parameters.

list_filtersA

Discover which category-specific filter attributes (and sample values) exist for a search query. Call this BEFORE search_offers when the user mentions an attribute like resolution, capacity, brand, etc., so you can pass valid keys in filters. If the query could match several categories (e.g. 'ssd' also hits laptops), pass category_id from list_categories() to sample only that category.

Inputs: query (required), limit, category_id. Returns: result

list_regionsA

List OLX regions (oblasts) and major cities with their ids, for search_offers region_id/city_id.

Inputs: no named parameters.

prom_search_offersA

Search Prom.ua (Ukrainian B2C marketplace) and return matching products. Returns 'total', 'returned', 'offers'}; each offer has id, title, price (UAH), currency, url. Prom sells new products from shops (like Hotline). For used/individual listings use search_offers (OLX).

Inputs: query (required), limit, offset, max_price, +1 more.

search_offersA

Search OLX.ua (Ukrainian classified ads) and return a page of matching offers plus the total count. Returns {'total', 'returned', 'offers'}; each offer has id, title, price (UAH), currency, location, url. For category-specific attributes (brand, resolution, capacity, ...) call list_filters(query) FIRST, then pass the keys via filters. For region/city ids call list_regions(); for a category id call list_categories(). For comparing prices of a new product across shops, also call hotline_search_offers and prom_search_offers. For Rozetka, use the brightdata MCP server's browser tools.

Inputs: query (required), sort, limit, state, +8 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 7 tools

    Disambiguation3/5

    The three search tools (search_offers, hotline_search_offers, prom_search_offers) are differentiated by platform (OLX, Hotline, Prom), which helps, but their descriptions overlap significantly—all return offers with similar fields. The guidance about when to call which is helpful but adds complexity. The other tools (get_offer_details, list_filters, list_categories, list_regions) are clearly distinct.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (e.g., search_offers, hotline_search_offers, get_offer_details, list_filters). The pattern is uniform and predictable, making it easy for an agent to infer functionality from the name.

    Tool Count5/5

    With 7 tools covering search across three platforms, details retrieval, and lookup utilities (categories, regions, filters), the number is well-scoped. Each tool serves a clear purpose without being excessive or insufficient for the domain of Ukrainian classified/marketplace searches.

    Completeness4/5

    The tool set provides a solid core for searching across multiple Ukrainian marketplaces, retrieving details, and exploring filters. Missing features include user account actions (posting, deleting offers) and cross-platform price comparison aggregation, but the stated focus is search, so these gaps are minor.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to search and retrieve listings from Sweden's largest second-hand marketplaces, Blocket and Tradera. Returns unified data including prices, images, seller information, and direct links to listings.
      9
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude to search and analyze product listings from multiple French marketplaces, evaluating price, delivery, and distance to a reference point to find the best value.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for OLX marketplace. Enables AI assistants to search listings, get offer details, track prices over time, and compare offers across OLX Poland and other supported countries.
      68 npm
      4
      MIT