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/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/plugins/askads/mcp-yandex-direct/plugin)<a href="https://agentmods.dev/plugins/askads/mcp-yandex-direct/plugin"><img src="https://agentmods.dev/badge/plugins/askads/mcp-yandex-direct/plugin/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/askads/mcp-yandex-direct/plugin"><img src="https://agentmods.dev/badge/plugins/askads/mcp-yandex-direct/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-yandex-direct 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "mcp-yandex-direct",
"displayName": "Yandex Direct MCP",
"version": "1.5.2",
"description": "Work with a Yandex Direct account from Claude: campaigns, ad groups, ads, keywords, bids and report statistics.",
"author": {
"name": "gistrec",
"url": "https://gistrec.cloud"
},
"homepage": "https://github.com/askads/mcp-yandex-direct#readme",
"repository": "https://github.com/askads/mcp-yandex-direct",
"license": "MIT",
"privacyPolicyUrl": "https://askads.ru/privacy-policy",
"keywords": [
"yandex-direct",
"advertising",
"marketing",
"ppc"
],
"userConfig": {
"token": {
"type": "string",
"title": "Yandex Direct OAuth token",
"description": "OAuth token for the Yandex Direct API. Stored in your operating system's credential store, never in settings.json. Leave empty to sign in from the conversation instead.",
"sensitive": true,
"default": ""
},
"login": {
"type": "string",
"title": "Client login",
"description": "Client login to operate on when the token belongs to an agency account. Leave empty to use the token's own account.",
"default": ""
},
"sandbox": {
"type": "string",
"title": "Sandbox mode",
"description": "Set to true to run against the Yandex Direct sandbox, where writes do not spend real money. Leave as false for the live account.",
"default": "false"
},
"telemetry": {
"type": "string",
"title": "Anonymous telemetry",
"description": "Set to 0 to disable the anonymous usage telemetry the server sends by default. Leave as 1 to keep it on.",
"default": "1"
}
},
"mcpServers": {
"yandex-direct": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"YANDEX_DIRECT_TOKEN": "${user_config.token}",
"YANDEX_DIRECT_LOGIN": "${user_config.login}",
"YANDEX_DIRECT_SANDBOX": "${user_config.sandbox}What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.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.
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 · 63 lines scan A faaf13076958
mcp-yandex-direct is a plugin published in the GitHub repository askads/mcp-yandex-direct (3 stars, last pushed 2d 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 2026-10-04.
Other plugins, from other repositories
vcfa-orchestrator
Skills that drive the VCF Automation Orchestrator MCP server safely: discovery-first authoring, package-first publishing, and guided troubleshooting via the server's vcfa- prompts and tools.
mailchimp-mcp-server
Draft, test, and send Mailchimp campaigns straight from your MCP client — with audience management, subscriber CRUD, and post-send analytics behind safe-by-default send gates. STDIO or Streamable HTTP.
osrs-wiki-mcp
Source-backed Old School RuneScape Wiki research through ten read-only MCP tools.
mcp-yandex-audience
An MCP server that lets an AI application work with Yandex Audiences, Yandex's advertising-audience service. It can create customer and lookalike segments, and manage pixels and access settings.
sanction
Independent authorization plane for AI agents — approve, escalate, or deny spend, tools, credentials, and provisioning. Wires the hosted wallet MCP; the host must ask before acting.
better-godot-mcp
Comprehensive Godot Engine integration — 17 tools for game development.