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 askads/mcp-yandex-direct --skill direct-auditgit clone --depth 1 https://github.com/askads/mcp-yandex-directWrote 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/askads/mcp-yandex-direct/direct-audit)<a href="https://agentmods.dev/skills/askads/mcp-yandex-direct/direct-audit"><img src="https://agentmods.dev/badge/skills/askads/mcp-yandex-direct/direct-audit/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/askads/mcp-yandex-direct/direct-audit"><img src="https://agentmods.dev/badge/skills/askads/mcp-yandex-direct/direct-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00324 |
| Opus 5.5 | $0.00000 | $0.00130 |
| Sonnet 5.5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
direct-audit 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 13d 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
Yandex Direct MCP
What this server covers
Yandex Direct is one advertiser's ad account: search and networks. It is not Yandex Metrica — there is no web analytics here. New campaigns and ads can only be created as text ones, but objects of any type can be listed, renamed, re-budgeted, paused, archived and deleted by id.
Check whose account you are in
An agency token operates on the agency's own account until a client login is set. Check that before trusting an empty campaign list — an empty result usually means the wrong account, not an empty account.
Filtering campaigns
A type filter that omits UNIFIED_CAMPAIGN hides current performance campaigns. When
listing campaigns to answer "what is running", do not filter by type at all.
Quota and statistics
Every call spends the daily Units quota; get_quota shows what is left. Statistics run as
an asynchronous task in the Reports service, which has its own daily limits. Request
one wide period rather than looping over days or campaigns.
Writes spend real money
Unless sandbox mode is on, writes spend real money and deletion is irreversible. A partially failed batch still returns HTTP 200 — read the per-object errors and retry only the objects that failed, never the whole batch.
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.
- 13d ago First seen · 38 lines · 0 tokens per session scan A 87a18440773a
direct-audit is a skill published in the GitHub repository askads/mcp-yandex-direct (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 324 tokens. 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 2026-10-04.
Other skills, from other repositories
okx-cex-portfolio
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…
okx-cex-trade
Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode'…
okx-sentiment-tracker
Use this skill when the user asks about: 'any crypto news', 'latest news', 'market update', 'daily briefing', 'BTC news', 'ETH news', 'news on SOL', 'search SEC ETF', 'regulation news', 'Bitcoin halving', 'is BTC bullish or bearish', 'coin sentiment', 'sentiment trend', 'trending coins', 'top bullish coins', 'bearish…
okx-cex-earn
A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.
okx-cex-market
Use this skill when the user asks for: price of any asset, ticker, order book, candles, OHLCV, funding rate, open interest, OI change scanner, market screener (top movers, high-volume, newly listed), mark price, index price, recent trades, instrument list, stock tokens, metals prices (gold, XAU, XAG), commodities…
okx-cex-smartmoney
An OKX tool for studying activity from high-performing traders, sometimes called “smart money.” It shows trader rankings, positions, trades, past results, and combined signals.