Borrowing it
Nothing to install: this file belongs to serezhenkov-lab/1c-ai-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.
curl -O https://raw.githubusercontent.com/serezhenkov-lab/1c-ai-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/serezhenkov-lab/1c-ai-mcpWrote 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/serezhenkov-lab/1c-ai-mcp/claude-md)<a href="https://agentmods.dev/instructions/serezhenkov-lab/1c-ai-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/serezhenkov-lab/1c-ai-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.
<a href="https://agentmods.dev/instructions/serezhenkov-lab/1c-ai-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/serezhenkov-lab/1c-ai-mcp/claude-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 | $0.01687 | $0.01687 |
| Opus 5 | $0.00843 | $0.00843 |
| Sonnet 5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
1c-ai-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.
How it starts
The opening of the file, as written. The whole thing — 91 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
MCP-сервер (Model Context Protocol) для интеграции с API 1С:Напарник (code.1c.ai). Построен на FastMCP (Python), упакован в Docker. Предоставляет 12 инструментов: анализ кода (check_1c_code, ask_1c_ai, explain_1c_syntax, review_1c_code, rewrite_1c_code, modify_1c_code) и документация (its_help, fetch_its, search_1c_documentation, onec_help, diff_1c_documentation_versions, config_help) - все через HTTP API 1С:Напарник.
Основан на идее comol/1c-code-checker с исправлениями формата API-запросов (ошибки 422), заимствованными из SteelMorgan/spring-mcp-1c-copilot.
Architecture
main.py ← точка входа, запуск FastMCP
src/
mcp_server.py ← определение MCP-инструментов (@mcp.tool)
onec_api_client.py ← HTTP-клиент к API 1С:Напарник (httpx + SSE)
Dockerfile ← основной Dockerfile (python:3.11-slim)
docker-compose.yml ← compose для запуска
tests/ ← тестовые скрипты
Поток данных: MCP-клиент (Cursor/Claude Code) → FastMCP HTTP endpoint (:8007/mcp) → mcp_server.py (tool handlers) → OneCApiClient → code.1c.ai API (SSE stream) → парсинг ответа → возврат клиенту.
Сессии: OneCApiClient управляет пулом conversation sessions (создание, переиспользование, TTL-очистка, лимит активных).
API 1С:Напарник:
POST /chat_api/v1/conversations/— создание дискуссии (поля:tool_name,skill_name,is_chat)POST /chat_api/v1/conversations/{id}/messages— отправка сообщения (SSE-ответ), content:{content: {instruction: "..."}}
Build & Run
# Docker build
docker build -t 1c-ai-mcp .
# Docker run
docker run -d -p 8007:8007 -e ONEC_AI_TOKEN="token" 1c-ai-mcp
# Docker Compose
docker compose up -d
# Local dev
pip install -r requirements.txt
ONEC_AI_TOKEN="token" python main.py
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
ONEC_AI_TOKEN |
Yes* | — | API-токен 1С:Напарник |
ONEC_AI_TOKEN_FILE |
No | — | Путь к файлу с токеном (Docker Secrets, приоритет над TOKEN) |
ONEC_AI_BASE_URL |
No | https://code.1c.ai |
Базовый URL API |
ONEC_AI_SKILL_NAME |
No | raw |
Skill для создания дискуссий (raw, custom) |
ONEC_AI_AUTH_FORMAT |
No | plain |
Формат Authorization header (plain / bearer) |
ONEC_AI_TIMEOUT |
No | 120 |
Таймаут HTTP-запросов (сек) |
ONEC_CONFIG_NAME |
No | — | Конфигурация по умолчанию для config_help (например, "ERP", "ЗУП") |
HTTP_PORT |
No | 8007 |
Порт MCP-сервера |
USESSE |
No | false |
Транспорт: true=SSE, false=streamable-http |
MAX_ACTIVE_SESSIONS |
No | 10 |
Лимит активных сессий |
SESSION_TTL |
No | 3600 |
TTL сессии (сек) |
MCP_TOOL_CALL_MODE |
No | standard |
Режим вызова upstream: standard (промпты) / direct (прямой вызов инструментов) |
ONEC_AI_INPUT_MAX_LENGTH |
No | 100000 |
Макс. длина входных данных (символов) |
LOG_LEVEL |
No | INFO |
Уровень логирования (DEBUG, INFO, WARNING) |
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 · 91 lines · 1,687 tokens per session scan A 7c8c62553e95
1c-ai-mcp CLAUDE.md is an instructions file published in the GitHub repository serezhenkov-lab/1c-ai-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 1,687 tokens to every session, about $0.0084 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
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).
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.
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).
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.