mcp-yandex-direct: Instructions file for Claude Code

CLAUDE.md

mcp-yandex-direct CLAUDE.md is an instructions file for Claude Code from askads/mcp-yandex-direct. It costs 1,836 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that connects coding agents to the Yandex Direct advertising API.

In plain words
What is it for?
Use them when developing, testing, building, or adding tools to the Yandex Direct integration.
Why use it?
They explain the available commands, API structure, authentication, retries, pagination, and conventions needed to change the server safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is askads/mcp-yandex-direct's own configuration. It tells Claude Code how to work on mcp-yandex-direct itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-yandex-direct configures →

Reuse

Borrowing it

Nothing to install: this file belongs to askads/mcp-yandex-direct. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/askads/mcp-yandex-direct/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/askads/mcp-yandex-direct

Made for: Claude Code.

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.

agentmods badge for mcp-yandex-direct CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/askads/mcp-yandex-direct/claude-md/github.svg)](https://agentmods.dev/instructions/askads/mcp-yandex-direct/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/askads/mcp-yandex-direct/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-direct/claude-md/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.

agentmods 80×15 button for mcp-yandex-direct CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/askads/mcp-yandex-direct/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-direct/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,836 This file is loaded in full into every session.
When invoked 1,836 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01836 $0.01836
Opus 5 $0.00918 $0.00918
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00184 $0.00184

Measured 8d ago against content hash cbf5471eda68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-yandex-direct CLAUDE.md 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 8d 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.

CLAUDE.md · 114 lines

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.

CLAUDE.md — mcp-yandex-direct

MCP server for the Yandex Direct API v5 (TypeScript, stdio). Tools wrap the JSON services; raw_request is the escape hatch for everything without a dedicated tool.

Commands

npm run dev        # run from source (tsx watch)
npm test           # unit tests, no network
npm run typecheck  # types for src + tests
npm run build      # emit dist/
npm run smoke      # live READ-ONLY calls (needs YANDEX_DIRECT_TOKEN)

More detail in docs/DEVELOPMENT.md. Tool list: docs/TOOLS.md.

Architecture

  • src/client.ts — HTTP client: timeout, retry/backoff, Units quota, getAll cursor pagination, report polling. Every request path (call/callV4/report) resolves the token through the TokenStore per request; a missing token raises AuthRequiredError before building the request, the retries and fetch. An authorization error (code 53) on a stored token triggers one silent refresh + replay per request.
  • src/oauth.ts — the OAuth flow: PKCE pair (S256), authorize URL against https://oauth.yandex.ru/verification_code, code exchange and refresh. No client_secret — this is a public client, and a secret inside an npm package would protect nothing. The pending verifier lives in one module-level slot (one stdio server = one user); a second start_login replaces it.
  • src/credentials.ts~/.config/mcp-yandex-direct/credentials.json, mode 0600. An unparsable file reads as "not connected", never as an empty token.
  • src/auth.tsTokenStore: resolves the token per request (env wins over stored), refreshes on expiry, and raises AuthRequiredError whose message is the product — it is the only text the user ever sees about a missing token, and it names both fixes (start_login, env variable).
  • src/tools/*.ts — one file per service, each exports register<Name>Tools(server, client); src/tools/auth.ts (auth_status, start_login, finish_login, logout) additionally takes the TokenStore.
  • src/tools/util.ts — shared helpers (see conventions below).
  • src/index.ts — wires every register* into the McpServer. loadConfigOrDegraded starts the server even on a config problem; without a token the initialize instructions open with the unconfigured prefix (connect via start_login, or set YANDEX_DIRECT_TOKEN and restart).
  • src/telemetry.ts — anonymous usage pings (ids/names/versions only, never data or arguments; fire-and-forget, must never block or throw; opt-out ASKADS_TELEMETRY=0). server_start means "a usable install started"; an install without a token sends unconfigured_start instead. The reason is a closed vocabulary (missing_token, …) — never a variable's name or value. startup_failed remains for a config unusable at load time (malformed values), also fire-and-forget.
  • src/config.ts — env → config. A missing YANDEX_DIRECT_TOKEN is NOT an error: the field stays undefined, the token is resolved per request (env → stored credentials) and the client raises AuthRequiredError at call time. ConfigError (with a reason code) is reserved for malformed values, caught by loadConfigOrDegraded in index.ts (no such checks exist today — the optional variables fall back to defaults on junk).

Read the full file on GitHub · 114 lines

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.

  1. 8d ago First seen · 114 lines · 1,836 tokens per session scan A cbf5471eda68

Subscribe to this mod's changes

mcp-yandex-direct CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-yandex-direct (1 stars, last pushed 18d ago), licensed MIT. It adds 1,836 tokens to every session, about $0.0092 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 2026-08-31.

Related

Other instructions, from other repositories

data-scientist copilot-instructions.md

Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.

realnghon/data-scientist · 373 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens