Borrowing it
Nothing to install: this file belongs to Bazilio-san/mcp-vkusvill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Bazilio-san/mcp-vkusvill/master/AGENTS.mdgit clone --depth 1 https://github.com/Bazilio-san/mcp-vkusvillWrote 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.
[](https://agentmods.dev/instructions/bazilio-san/mcp-vkusvill/agents-md)<a href="https://agentmods.dev/instructions/bazilio-san/mcp-vkusvill/agents-md"><img src="https://agentmods.dev/badge/instructions/bazilio-san/mcp-vkusvill/agents-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.
<a href="https://agentmods.dev/instructions/bazilio-san/mcp-vkusvill/agents-md"><img src="https://agentmods.dev/badge/instructions/bazilio-san/mcp-vkusvill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01793 | $0.01793 |
| Opus 5 | $0.00897 | $0.00897 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
mcp-vkusvill AGENTS.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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-vkusvill
Guidance for AI agents working in this repository.
What This Is
An MCP (Model Context Protocol) server built on the fa-mcp-sdk framework. It proxies the official
VkusVill MCP API (https://mcp001.vkusvill.ru/mcp) and reformats its raw JSON responses into
readable Markdown. Exposed over STDIO or HTTP/SSE transports.
The upstream is itself an MCP server (JSON-RPC 2.0 over Streamable HTTP, anonymous — no auth). This
server performs the MCP handshake with it, forwards tools/call, and formats the result.
Tools
All 7 upstream tools are proxied (our tool → upstream tool):
| Our tool | Upstream tool | Purpose |
|---|---|---|
search_products |
vkusvill_products_search |
Text search (price, rating, weight, id, xml_id, url) |
get_product_details |
vkusvill_product_details |
Composition, КБЖУ, allergens, shelf life, manufacturer |
get_product_analogs |
vkusvill_product_analogs |
Similar / replacement products |
get_discounts |
vkusvill_products_discount |
Promo items with old→new price |
find_shops |
vkusvill_shops |
Shops + filter reference (region/city/metro ids) |
search_recipes |
vkusvill_recipes |
Recipes (ingredients, steps, nutrition) + filter reference |
create_cart_link |
vkusvill_cart_link_create |
Build a shareable cart link from {xml_id, quantity} |
Tool-level upstream errors arrive as {ok:false, error}; they are surfaced to the LLM via
asTextError (not thrown as JSON-RPC errors).
Architecture
src/
├── start.ts # Entry point — assembles McpServerData, calls initMcpServer()
├── _types_/
│ ├── common.d.ts # IToolModule interface
│ └── custom-config.ts # Custom AppConfig extensions
├── lib/
│ ├── vkusvill-client.ts # MCP client to the upstream (handshake, retry, SSE/JSON parse, errors)
│ └── format.ts # Markdown formatters for every payload type (the core value)
├── tools/
│ ├── tools.ts # Registry + central dispatcher (handleToolCall)
│ ├── search-products.ts # One file per tool: definition + handler + optional prompt (IToolModule)
│ ├── get-product-details.ts
│ ├── get-product-analogs.ts
│ ├── get-discounts.ts
│ ├── find-shops.ts
│ ├── search-recipes.ts
│ └── create-cart-link.ts
├── prompts/
│ ├── agent-brief.ts # Short agent description
│ ├── agent-prompt.ts # Full system prompt
│ └── tool-prompts.ts # Aggregates per-tool prompts for the tool_prompt MCP prompt
└── api/router.ts # REST endpoints (tsoa decorators) — health only
config/
├── default.yaml # Base config (incl. accessPoints.vkusvillMcp — the upstream host)
├── development.yaml / production.yaml # Env overrides
├── local.yaml # Local secrets / dev overrides (gitignored)
└── custom-environment-variables.yaml # Env var → config mapping
tests/mcp/ # MCP tool tests (STDIO, HTTP, SSE) — test-cases.js is shared
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.
- 12d ago First seen · 140 lines · 1,793 tokens per session scan A 8f9d71ce44b3
mcp-vkusvill AGENTS.md is an instructions file published in the GitHub repository Bazilio-san/mcp-vkusvill (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,793 tokens to every session, about $0.0090 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.
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.
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.
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.
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).
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.
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).