A set of instructions for using an installed VK Ads connection to inspect, analyze, research, and explicitly change VK advertising data. VK Ads is an advertising platform and VK communities are public groups on VK.

For reviewing campaigns, ads, audiences, statistics, forecasts, leads, surveys, price lists, tokens, and public VK communities.

It defines how to check connections, understand campaign data, prepare changes, and require confirmation before supported updates.

vk-ads-mcp — Skill for Codex by sergeylopukhov/vk-ads-mcp-all-in-one

Install

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.

Any agent

npx skills add sergeylopukhov/vk-ads-mcp-all-in-one --skill codex-skill

Clone the repo

git clone --depth 1 https://github.com/sergeylopukhov/vk-ads-mcp-all-in-one

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill/github.svg)](https://agentmods.dev/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill)

Your own site

<a href="https://agentmods.dev/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill"><img src="https://agentmods.dev/badge/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill"><img src="https://agentmods.dev/badge/skills/sergeylopukhov/vk-ads-mcp-all-in-one/codex-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,369 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.01369
Opus 5.5	$0.00028	$0.00548
Sonnet 5.5	$0.00014	$0.00274
Haiku 4.5	$0.00007	$0.00137

Measured 2mo ago against content hash 59f1da817a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vk-ads-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 2mo 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.

codex-skill/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VK Ads MCP

Use only public tools exposed by the installed vk-ads server. Do not invent tool names, provider fields, object IDs, or results.

Core procedure

For the first advertising operation, call vk_ads_connection_check. Skip it for community-only work because those tools use a separate Core VK token.
Infer safe missing parameters from read tools and the conversation. Ask only when a value cannot be inferred reliably or changes the user's decision.
For analysis, establish the object hierarchy and reporting period before interpreting metrics. Prefer complete periods and disclose partial data.
Call write tools only when the user explicitly requests that exact change.
Before every supported write, call vk_ads_action_prepare with the intended action and the exact input. Read ActionReadiness; do not infer missing provider requirements from a failed write.
If ready=false, report the concrete missing or incompatible condition. Apply a suggestedPatch to a related object only after separate user confirmation when requiresConfirmation=true.
When ready=true, use one narrow write call with the same input. Never cycle through creatives or repeat a write based on a guess. Reread the result when supported.
Never expose tokens, client secrets, identifier-file contents, lead contacts, respondent answers, or raw private provider payloads.
Respond in Russian unless the user requests another language.

Live status

Treat the installed release's docs/tools.md as the status authority.

A ✅ tool may be used normally within the rules above.
A ⛔️ read tool may be attempted when useful, but disclose its status before use and report the result without describing the tool as available.
Do not use a ⛔️ write tool as a routine solution. The OAuth recovery exceptions below still require an explicit user request. Do not use other ⛔️ write tools.
Never treat an expected failure, empty mutation, or remoderated=false as success.

Read the full file on GitHub · 115 lines

Files

What ships with it

5 files beside SKILL.md 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.

Changes

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.

2mo ago First seen · 115 lines · 70 tokens per session scan A 59f1da817a23

Subscribe to this mod's changes

vk-ads-mcp is a skill published in the GitHub repository sergeylopukhov/vk-ads-mcp-all-in-one (0 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,369 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Marketing and SEO

vk-ads-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vk-ads-mcpsergeylopukhov/vk-ads-mcp-all-in-one	Skill	0	3mo ago	MIT	A	70	Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code