What is yandex-tools-mcp CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, in a monorepo—a single repository containing several related packages. They describe the Yandex API servers, setup commands, tests, and code-quality checks.

Use it when contributing to the Yandex MCP servers, especially to install packages, run tests, check formatting, or start a server locally.

They give the coding assistant and developers a shared reference for how this repository is organised and how to work on it. This reduces guesswork when installing dependencies, testing changes, or running a server.

How seyka-ai/yandex-tools-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to seyka-ai/yandex-tools-mcp. 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/seyka-ai/yandex-tools-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/seyka-ai/yandex-tools-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/seyka-ai/yandex-tools-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/seyka-ai/yandex-tools-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/seyka-ai/yandex-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/seyka-ai/yandex-tools-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/seyka-ai/yandex-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/seyka-ai/yandex-tools-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,648 This file is loaded in full into every session.

When invoked 2,648 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.

Model	Per session	Once invoked
Fable 5.1	$0.02648	$0.02648
Opus 5.5	$0.01059	$0.01059
Sonnet 5.5	$0.00530	$0.00530
Haiku 4.5	$0.00265	$0.00265

Measured 9d ago against content hash e76efce343f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yandex-tools-mcp 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

yandex-tools-mcp CLAUDE.md — 88% identical, 0 lines differ

CLAUDE.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Monorepo containing five MCP (Model Context Protocol) servers for Yandex APIs:

yandex-search-mcp: Web search optimized for Russian/Cyrillic content
yandex-wordstat-mcp: Keyword research and search trend analysis (Wordstat v2 via the Yandex Cloud Search API)
yandex-webmaster-mcp: Site analytics, indexing status, and SEO diagnostics
yandex-metrika-mcp: Web analytics, traffic data, and visitor insights
yandex-direct-mcp: PPC campaign management — campaigns, ad groups, ads, keywords, bids, statistics (the only server with real-money writes)

Commands

# Install dependencies (from root)
bun install

# Tests (runs the `test` script in every package that has one)
bun run test

# Code quality
bun run lint          # Check code style with Biome
bun run lint:fix      # Fix linting issues
bun run format        # Format code

# Run servers locally (for testing)
YANDEX_SEARCH_API_KEY=key YANDEX_FOLDER_ID=folder node packages/yandex-wordstat-mcp/src/index.mjs
YANDEX_SEARCH_API_KEY=key YANDEX_FOLDER_ID=folder node packages/yandex-search-mcp/src/index.mjs
YANDEX_WEBMASTER_TOKEN=token node packages/yandex-webmaster-mcp/src/index.mjs
YANDEX_METRIKA_TOKEN=token node packages/yandex-metrika-mcp/src/index.mjs
YANDEX_DIRECT_TOKEN=token node packages/yandex-direct-mcp/src/index.mjs   # defaults to sandbox; YANDEX_DIRECT_LIVE=1 for production

# Publish packages
cd packages/yandex-wordstat-mcp && npm publish
cd packages/yandex-search-mcp && npm publish
cd packages/yandex-webmaster-mcp && npm publish
cd packages/yandex-metrika-mcp && npm publish
cd packages/yandex-direct-mcp && npm publish

Architecture

Tech Stack

Node.js >= 18.0.0
Bun package manager (monorepo workspaces)
Pure ES Modules (no TypeScript, no build step)
Biome for linting/formatting

Package Structure

packages/
├── yandex-search-mcp/src/index.mjs     # Single-file MCP server (1 tool: search)
├── yandex-wordstat-mcp/
│   ├── src/
│   │   ├── index.mjs                   # MCP server (5 tools)
│   │   └── convert.mjs                 # Pure v2 wire-format conversion helpers
│   └── test/
│       └── conversions.test.mjs        # bun test for convert.mjs
├── yandex-webmaster-mcp/
│   └── src/
│       ├── index.mjs                   # MCP server (34 tools)
│       └── auth.mjs                    # OAuth token exchange flow
├── yandex-metrika-mcp/
│   └── src/
│       ├── index.mjs                   # MCP server (44 tools)
│       └── auth.mjs                    # OAuth token exchange flow
└── yandex-direct-mcp/                  # Multi-file (unlike siblings): ~20 tools split by resource
    ├── src/
    │   ├── index.mjs                   # Thin entry: CLI dispatch, build client, register tool groups
    │   ├── auth.mjs                    # OAuth token exchange flow
    │   ├── client.mjs                  # v5 directRequest + Reports reportRequest + Live4 liveV4Request
    │   ├── money.mjs                   # toMicro/fromMicro (micro-unit conversion)
    │   ├── format.mjs                  # summarizeResults (mutation result formatter), today()
    │   ├── ids.mjs                     # Exact int64 IDs: parseJson/toJson/idSchema
    │   └── tools/                      # campaigns, adgroups, ads, images, keywords, reports, account
    └── test/
        └── ids.test.mjs                # bun test for ids.mjs

Read the full file on GitHub · 210 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.

9d ago First seen · 210 lines · 2,648 tokens per session scan A e76efce343f5

Subscribe to this mod's changes

yandex-tools-mcp CLAUDE.md is an instructions file published in the GitHub repository seyka-ai/yandex-tools-mcp (70 stars, last pushed 9d ago), licensed MIT. It adds 2,648 tokens to every session, about $0.0106 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 2026-10-28.

Claude Code Project management claude keyword-research mcp mcp-server model-context-protocol

yandex-tools-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
yandex-tools-mcp CLAUDE.mdseyka-ai/yandex-tools-mcp	Instructions file	70	9d ago	MIT	A	2,648	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

yandex-tools-mcp: Instructions file for Claude Code