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/ilyautov/marketplaces-mcp-ruWrote 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/plugins/ilyautov/marketplaces-mcp-ru/gemini-extension)<a href="https://agentmods.dev/plugins/ilyautov/marketplaces-mcp-ru/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ilyautov/marketplaces-mcp-ru/gemini-extension/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/plugins/ilyautov/marketplaces-mcp-ru/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ilyautov/marketplaces-mcp-ru/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
marketplaces-mcp-ru 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- marketplaces-mcp-ru — 100% identical, 12 lines differ
What it actually says
{
"name": "marketplaces-mcp-ru",
"version": "0.6.1",
"description": "MCP-серверы для кабинетов Wildberries, Ozon, Яндекс Маркета и Авито: 1022 метода Seller API, safety-гейт на запись, поиск по-русски. MCP servers for Wildberries, Ozon, Yandex Market and Avito seller accounts.",
"mcpServers": {
"wildberries": {
"command": "python3",
"args": ["${extensionPath}/serve.py", "wb"]
},
"ozon": {
"command": "python3",
"args": ["${extensionPath}/serve.py", "ozon"]
},
"ozon-perf": {
"command": "python3",
"args": ["${extensionPath}/serve.py", "ozon-perf"]
},
"yandex-market": {
"command": "python3",
"args": ["${extensionPath}/serve.py", "yandex"]
},
"avito": {
"command": "python3",
"args": ["${extensionPath}/serve.py", "avito"]
}
},
"contextFileName": "GEMINI.md"
}
What ships with it
24 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/logo-400.png 12 KB
- assets/logo.svg 574 B
- assets/social-preview.png 47 KB
- scripts/avito_specs/autoload.openapi.json 121 KB
- scripts/avito_specs/ops_messenger.json 4.0 KB
- scripts/avito_specs/ops_orders.json 4.3 KB
- scripts/avito_specs/ops_promotion.json 2.5 KB
- scripts/avito_specs/ops_ratings.json 1.2 KB
- scripts/avito_specs/ops_user_stock_item.json 5.9 KB
- scripts/build_marketplace_pages.py 48 KB runs code
- scripts/derive_pagination.py 5.2 KB runs code
- scripts/fix_items_path_from_examples.py 9.0 KB runs code
- scripts/ingest_avito.py 5.2 KB runs code
- scripts/ingest_openapi.py 12 KB runs code
- scripts/ingest_ozon.py 4.3 KB runs code
- scripts/ingest_specs.py 4.8 KB runs code
- scripts/make_social_preview.py 3.8 KB runs code
- scripts/package_mcpb.py 4.3 KB runs code
- scripts/package_release.py 6.3 KB runs code
- scripts/security/forbid_sensitive_files.py 2.3 KB runs code
- scripts/security/scan_mcp_config.py 5.8 KB runs code
- scripts/smoke_mcp.py 2.4 KB runs code
- scripts/sync_swagger.py 3.6 KB runs code
- scripts/validate_items_path.py 3.5 KB runs code
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 Changed 34b8cdf0b1b3
- 1mo ago Changed · +8 lines 05a8e747a093
- 1mo ago First seen · 21 lines scan A 8fea7554ec72
marketplaces-mcp-ru is a plugin published in the GitHub repository ilyautov/marketplaces-mcp-ru (51 stars, last pushed 9d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-07.
Other plugins, from other repositories
polar-skills
Official Polar skills for billing, subscriptions, and local development.
stripe-skills
Official Stripe skills for payments, billing, Connect, Apps, and API upgrades.
utopia-gtm
Go-to-Market — seven sub-modules (Growth Strategy, Marketing & Comms, Sales Enablement, Customer Success, BD & Partnerships, GTM Engineering, IP Commercialisation). Positioning, outbound, signals, content, paid, RevOps, retention, and agent governance.
utopia-investments
Investments — due diligence, financial modeling, valuation, capital markets, fundraising decks, and quant pricing, plus the founder-side investor reading room. For funds team and fundraising.
shopify-app-builder
Shopify app development with 36 skills, 17 guided commands and 8 specialist agents; local context, resume, feedback and visual reports. No bundled MCP or tracking.
agentshare-commerce-mcp
11 MCP tools on agent-paid rails: dual-auth / x402, commerce procurement (search, bestoffer, commercequote), secondary Solana/Meteora demos. Start building at agentshare.dev/signup.