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.
npx skills add Vladimir-Human/ru-marketplace-mcp --skill mpstats-connectorgit clone --depth 1 https://github.com/Vladimir-Human/ru-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/skills/vladimir-human/ru-marketplace-mcp/mpstats-connector)<a href="https://agentmods.dev/skills/vladimir-human/ru-marketplace-mcp/mpstats-connector"><img src="https://agentmods.dev/badge/skills/vladimir-human/ru-marketplace-mcp/mpstats-connector/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/skills/vladimir-human/ru-marketplace-mcp/mpstats-connector"><img src="https://agentmods.dev/badge/skills/vladimir-human/ru-marketplace-mcp/mpstats-connector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.01542 |
| Opus 5 | $0.00063 | $0.00771 |
| Sonnet 5 | $0.00025 | $0.00308 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
mpstats-connector 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPStats Connector
Paid-account sales/stock analytics for Ozon and Wildberries items, via the
MPStats browser-plugin API (plugin.mpstats.io/pluginapi). Unlike the
anonymous catalog connectors in this workspace, this one is optional: it
needs a paid MPStats account configured as the MPSTATS_MP_AUTH env var (the
raw mp_auth JWT cookie from a logged-in browser plugin session at
mpstats.io). Without it the server boots cleanly, every tool returns
auth_missing, and no other connector is affected — like every source here,
it is a pleasant extra you opt into, not a requirement.
When to use
- Per-SKU 30-day sales analytics — orders graph, price graph, stock graph
- Current price and stock for an item (today's reading off the graph tail)
- Warehouse stock split — FBS (seller warehouse) vs FBO (marketplace warehouse)
- Seller/brand identity and a rolling orders-per-day average
- Sales-trend comparison across several SKUs in one batched call
When NOT to use
- Bare price/availability checks with no account — use
wb_card/ozon_card. - Reviews, categories, seller tax identity — MPStats does not surface those; use the catalog connectors.
- Search by text or category browsing — MPStats analytics is keyed by SKU, not by query.
Prerequisites
Set MPSTATS_MP_AUTH to the raw JWT (no mp_auth= prefix, no quotes):
export MPSTATS_MP_AUTH='eyJ0eXAiOiJKV1Qi...' # from a logged-in mpstats.io session
Without it, every tool returns an auth_missing error (retryable: false) and
the server still boots cleanly. Treat the token as a secret: it identifies a
paid, quota-billed account. Never log it, never commit it.
Tools available
mpstats_item(skus, place, oz_fbs=True)— per-SKU 30-day analytics. Up to 100 SKUs per call. Returns, per SKU:seller,seller_id,brand,stock_now,price_avg_rub,orders_per_day,days_on_stocks,totals(orders/sum/ sum_prev), and four per-day graphs (orders_graph,prices_graph,count_graph,rubrics_graph).mpstats_warehouses(skus, place)— per-SKU warehouse stock split:fbscount,fbototal (collapsed from the upstream per-warehouse list), the rawfbo_warehouseslist, and the upstreamlast_updatetimestamp.
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.
- 2d ago Changed · +6 lines b0e6e647c4c5
- 12d ago First seen · 108 lines · 126 tokens per session scan A 24b05d359faa
mpstats-connector is a skill published in the GitHub repository Vladimir-Human/ru-marketplace-mcp (93 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 1,542 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
commerce-detail-page-copy
A writing tool for Korean e-commerce product detail pages. It can generate a full 13-section page, assess an existing page, or create two persona-based copy sets.
commerce-detail-page-planner
A strategy brief for deciding what a Korean e-commerce product page should say, show, and prioritise. It defines the main message, opening, page structure, sales channel approach, and photo checklist before copy, code, or images are made.
commerce-integrated-strategy
An e-commerce planning skill that combines customer research, product messaging, and store data into a one-page sales strategy with three priority actions.
commerce-ad-claim-compliance-kr
A pre-publication check for Korean advertising and product-page wording. It reviews claims against South Korea's advertising, food-safety, and e-commerce laws.
commerce-automation-audit
A planning and consulting tool for finding automation opportunities in an online store. It reviews work such as products, pricing, orders, stock, marketing, and business data, then proposes priorities and a phased roadmap.