mcp-yandex-dostavka: Instructions file for Claude Code

CLAUDE.md

mcp-yandex-dostavka CLAUDE.md is an instructions file for Claude Code from A1-x-Tech/mcp-yandex-dostavka. It costs 2,169 tokens per session, scanned A, original, MIT.

A project instruction document for an MCP server, a program that exposes tools to other software, for the Yandex Delivery business API.

In plain words
What is it for?
Use it when developing, testing, type-checking, building, or adding a tool for Yandex Delivery’s express and platform API areas.
Why use it?
It gives contributors the project’s commands, architecture, environment variables, API boundaries, 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 A1-x-Tech/mcp-yandex-dostavka's own configuration. It tells Claude Code how to work on mcp-yandex-dostavka 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-dostavka configures →

Reuse

Borrowing it

Nothing to install: this file belongs to A1-x-Tech/mcp-yandex-dostavka. 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/A1-x-Tech/mcp-yandex-dostavka/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/A1-x-Tech/mcp-yandex-dostavka

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-dostavka CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a1-x-tech/mcp-yandex-dostavka/claude-md/github.svg)](https://agentmods.dev/instructions/a1-x-tech/mcp-yandex-dostavka/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-yandex-dostavka/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-yandex-dostavka/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-dostavka CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-yandex-dostavka/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-yandex-dostavka/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,169 This file is loaded in full into every session.
When invoked 2,169 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 $0.02169 $0.02169
Opus 5 $0.01085 $0.01085
Sonnet 5 $0.00434 $0.00434
Haiku 4.5 $0.00217 $0.00217

Measured 11d ago against content hash d9a619309306, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-yandex-dostavka 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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-yandex-dostavka

MCP server for the Yandex Delivery B2B API (TypeScript, stdio). A write API: tools create, accept and cancel real deliveries. Two independent contours behind one server: express (same-day claims — b2b.taxi.yandex.net, POST/GET /b2b/cargo/integration/v2/*) and platform (NDD / pickup points — b2b-authproxy.taxi.yandex.net, /api/b2b/platform/*). Auth on both is Authorization: Bearer <token> from the dostavka.yandex.ru cabinet; the shared YANDEX_DELIVERY_TOKEN can be overridden per contour. raw_request is the escape hatch for the ~30 endpoints without a dedicated tool.

Commands

npm run dev        # run from source (tsx watch)
npm test           # unit tests + dist smoke (incl. a real MCP handshake), no network
npm run typecheck  # types for src + tests
npm run build      # emit dist/
npm run smoke      # live READ-ONLY call (claims/search limit 1; needs YANDEX_DELIVERY_TOKEN)

Architecture

  • src/config.ts — env → config. Tokens: YANDEX_DELIVERY_TOKEN fills both contours, YANDEX_DELIVERY_EXPRESS_TOKEN / YANDEX_DELIVERY_PLATFORM_TOKEN override it. A missing token is NOT an error: the field stays undefined (an empty string reads as absent), the server starts degraded and the client raises CredentialsError (lives in types.ts) when a call needs that contour. ConfigError (with a reason code) is reserved for malformed values, caught by loadConfigOrDegraded in index.ts (no such checks exist today). Optional: *_BASE_URL per contour (platform test contour: b2b.taxi.tst.yandex.net), YANDEX_DELIVERY_LANG, YANDEX_DELIVERY_TIMEOUT_MS, YANDEX_DELIVERY_MAX_RETRIES.
  • src/client.ts — all HTTP. request(contour, method, path, {query, body, idempotent}) picks the base + Bearer token by contour (a bare contour throws CredentialsError right there — before the request is built, retried or sent; the message opens with the historical startup text verbatim and ends with the env-and-restart fix), builds the query string, sends Accept-Language, rejects paths that resolve to a foreign origin (SSRF guard), enforces an AbortController timeout that also covers reading the body, retries with backoff (honors Retry-After) and throws DeliveryError(status, body). One typed method per endpoint; claims/create mints a UUID request_id (query param) when the caller omits one.
  • src/tools/express.ts — the nine express_* tools; src/tools/platform.ts — the six platform_* tools; src/tools/raw.tsraw_request (contour + path + query + body). src/tools/util.tsok/fail, the READ_ONLY/WRITE/DESTRUCTIVE annotation presets and shared zod schema factories.
  • src/index.ts — wires every register* into the McpServer. loadConfigOrDegraded() catches ConfigError, pings startup_failed (fire-and-forget) and degrades the config to "no tokens"; a start with a missing token prepends the per-contour unconfigured prefix — plus Проблема конфигурации: <message> when a ConfigError was caught — to the initialize instructions, and oninitialized sends server_start for a fully configured install or unconfigured_start otherwise (reason in the old check order: with both contours bare it is missing_token, never a contour-specific code).
  • 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 missing a token sends unconfigured_start instead, and startup_failed remains for a config unusable at load time (malformed values). Every reason is a closed vocabulary (missing_token, missing_express_token, missing_platform_token) — never a variable's name or value.

Read the full file on GitHub · 126 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 · 126 lines · 2,169 tokens per session scan A d9a619309306

Subscribe to this mod's changes

mcp-yandex-dostavka CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-yandex-dostavka (0 stars, last pushed 12d ago), licensed MIT. It adds 2,169 tokens to every session, about $0.0108 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 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

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

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