Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/YegorMy/marketplace-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/yegormy/marketplace-mcp/marketplaces-mcp)<a href="https://agentmods.dev/mcp/yegormy/marketplace-mcp/marketplaces-mcp"><img src="https://agentmods.dev/badge/mcp/yegormy/marketplace-mcp/marketplaces-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/yegormy/marketplace-mcp/marketplaces-mcp"><img src="https://agentmods.dev/badge/mcp/yegormy/marketplace-mcp/marketplaces-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
marketplaces-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "marketplaces-mcp": { "command": "uvx", "args": [ "marketplaces-mcp" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 8 lines scan A fb6b97b754ce
marketplaces-mcp is an MCP server published in the GitHub repository YegorMy/marketplace-mcp (1 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
ru-marketplace-mcp
MCP server "ru-marketplace-mcp" as configured in Vladimir-Human/ru-marketplace-mcp. Runs in Docker (ghcr.io/vladimir-human/ru-marketplace-mcp:2.5.3).
secondhand-mcp
Search Facebook Marketplace, eBay, Depop, and Poshmark from AI — filters, photos, full listings. Runs locally from the secondhand-mcp npm package. Needs 3 environment variables to run.
marketplaces-mcp-ru
Wildberries, Ozon, Yandex Market & Avito seller APIs for AI assistants: schema-driven, safety-gated. Runs locally from the marketplaces-mcp-ru npm package. Needs 8 environment variables to run.
vinted-client
CLI and MCP server for the Vinted marketplace — search, items, sellers, price compare, trending. Runs locally from the @googlarz/vinted-client npm package.
bestprice-shopping
MCP server "bestprice-shopping", hosted remotely at mcp.bestprice.gr, as configured in TheBestCo/bestprice-mcp.
bol-mcp
MCP server for managing orders, offers, shipments, returns, and invoices via the bol.com Retailer API. Runs locally from the bol-mcp npm package.