mcp-yandex-metrica: Instructions file for Claude Code

CLAUDE.md

mcp-yandex-metrica CLAUDE.md is an instructions file for Claude Code from askads/mcp-yandex-metrica. It costs 1,691 tokens per session, scanned A, original, MIT.

Project instructions for a read-only connector to the Yandex Metrica API, a service that reports website traffic and usage. They document its commands, structure, conventions, and available tools.

In plain words
What is it for?
Use them when developing, testing, type-checking, building, or adding tools to the Yandex Metrica connector.
Why use it?
They give contributors the rules needed to understand the codebase and extend it without breaking its API client, authentication, pagination, retries, or tests.

Instructions file for Claude Code

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

This is askads/mcp-yandex-metrica's own configuration. It tells Claude Code how to work on mcp-yandex-metrica 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-metrica configures →

Reuse

Borrowing it

Nothing to install: this file belongs to askads/mcp-yandex-metrica. 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-metrica/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/askads/mcp-yandex-metrica

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-metrica CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/askads/mcp-yandex-metrica/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-metrica/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,691 This file is loaded in full into every session.
When invoked 1,691 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 $0.01691 $0.01691
Opus 5 $0.00846 $0.00846
Sonnet 5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured 11d ago against content hash 1cf5d0459f50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-yandex-metrica 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-yandex-metrica

MCP server for the Yandex Metrica API (TypeScript, stdio). Read-only MVP: tools wrap the Management and Reporting APIs; 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 call (needs YANDEX_METRIKA_TOKEN)

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

Architecture

  • src/client.ts — HTTP client over https://api-metrika.yandex.net (override with YANDEX_METRIKA_API_BASE): OAuth auth header, AbortController timeout, retry/backoff on 429 + 5xx (honors Retry-After), getAllStat limit/offset pagination of the Stat API, YandexMetrikaError(status, body). The client targets a full path ("management/v1/..." or "stat/v1/data") — Metrica has two API surfaces on one host.
  • 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-metrica/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.
  • src/tools/*.tsauth (auth_status, start_login, finish_login, logout), counters (list_counters, list_goals), statistics (get_statistics), raw (raw_request); each exports register<Name>Tools(server, client).
  • src/tools/util.ts — shared helpers (see conventions below).
  • src/index.ts — wires every register* into the McpServer.
  • 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). startup_failed is the exception: sendBlocking awaits it, because the caller exits right after and a fire-and-forget ping would die in flight. Its reason is a closed vocabulary (missing_token, …) — never a variable's name or value.
  • src/config.ts — env → config; throws ConfigError (with a reason code) instead of exiting, so index.ts can report the drop-off before dying.

Read the full file on GitHub · 107 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. 11d ago First seen · 107 lines · 1,691 tokens per session scan A 1cf5d0459f50

Subscribe to this mod's changes

mcp-yandex-metrica CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-yandex-metrica (2 stars, last pushed 21d ago), licensed MIT. It adds 1,691 tokens to every session, about $0.0085 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