What is ya-reviews-mcp CLAUDE.md?

Project instructions for a server that collects business reviews from Yandex Maps, a mapping service. It uses an automated browser and supports Playwright, an anti-detection browser option, or a separately running browser.

Use it to retrieve Yandex Maps reviews, choose a browser backend, connect to a remote browser, run the server over HTTP, or verify Python changes.

It gives developers the installation, launch, testing, linting, formatting, and type-checking commands needed to work on the review scraper.

How mrkhachaturov/ya-reviews-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrkhachaturov/ya-reviews-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/mrkhachaturov/ya-reviews-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mrkhachaturov/ya-reviews-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/mrkhachaturov/ya-reviews-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mrkhachaturov/ya-reviews-mcp/claude-md)

Your own site

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

Per session 1,332 This file is loaded in full into every session.

When invoked 1,332 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	$0.01332	$0.01332
Opus 5	$0.00666	$0.00666
Sonnet 5	$0.00266	$0.00266
Haiku 4.5	$0.00133	$0.00133

Measured 11d ago against content hash 639f7b1ec8d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ya-reviews-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 11d 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ya-reviews-mcp

MCP server that scrapes Yandex Maps business reviews via headless browser. Supports multiple backends: Playwright (default), Patchright (anti-detection), Remote CDP.

Commands

Command	Description
`uv sync --extra dev`	Install all dependencies (including dev)
`uv run playwright install chromium`	Install Chromium (required before first run)
`uv sync --extra patchright`	Install with Patchright backend
`uv run patchright install chromium`	Install Chromium for Patchright
`uv run ya-reviews-mcp`	Run server (stdio transport, Playwright default)
`uv run ya-reviews-mcp --backend patchright`	Run with Patchright backend
`uv run ya-reviews-mcp --backend remote --browser-url ws://localhost:9222`	Run with remote browser
`uv run ya-reviews-mcp --transport streamable-http --port 8000`	Run with HTTP transport
`uv run pytest`	Run tests
`uv run ruff check src/`	Lint
`uv run ruff format src/`	Format
`uv run mypy src/`	Type check (strict mode)

Architecture

src/ya_reviews_mcp/
  __init__.py           # CLI entry point (Click command)
  exceptions.py         # Exception hierarchy: MCPYaReviewsError → Scraping/PageNotFound/Browser
  reviews/
    config.py           # YaReviewsConfig — env-based settings dataclass
    models.py           # Pydantic models: Review, CompanyInfo, ReviewsResult
    scraper.py          # YaReviewsScraper — backend-agnostic DOM parsing
    backends/
      __init__.py       # BackendType enum + create_backend() factory (lazy imports)
      base.py           # BaseBrowserBackend ABC (start, close, new_context, handles_stealth)
      playwright_backend.py  # Standard Playwright backend
      patchright_backend.py  # Anti-detection Patchright fork (handles_stealth=True)
      remote_backend.py      # Remote CDP via WebSocket (auto-discovers debugger URL)
    fetchers/
      base.py           # BaseFetcher — JSON response formatting
      reviews.py        # ReviewsMixin — business logic (get_reviews, get_company_info, get_company_summary)
      fetcher.py        # YaReviewsFetcher — composite of Base + ReviewsMixin
  servers/
    main.py             # FastMCP instance + lifespan (browser lifecycle)
    tools.py            # @mcp.tool registrations (3 tools)
    context.py          # MainAppContext dataclass
    dependencies.py     # Dependency injection helper
  utils/
    decorators.py       # handle_scraper_errors decorator
    lifecycle.py        # Signal handlers (SIGTERM/SIGINT)
    logging.py          # Verbosity-based logging setup

Read the full file on GitHub · 102 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.

11d ago First seen · 102 lines · 1,332 tokens per session scan A 639f7b1ec8d5

Subscribe to this mod's changes

ya-reviews-mcp CLAUDE.md is an instructions file published in the GitHub repository mrkhachaturov/ya-reviews-mcp (3 stars, last pushed 6mo ago), licensed MIT. It adds 1,332 tokens to every session, about $0.0067 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.

Browser automation

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

ya-reviews-mcp: Instructions file for Claude Code