1C MCP

v1.0.0Business Applicationsstable

Инструмент для создания MCP-серверов в 1С:Предприятие путем разработки расширения конфигурации. Позволяет интегрировать данные и функциональность 1С с AI-ассистентами (Claude, Cursor и т.д.). Включает Python-прокси и пример расширения 1С с готовыми и

mcp1c1c-enterpriseaiawesome-list
Share:
402
Stars
0
Downloads
0
Weekly
0/5

What is 1C MCP?

1C MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to инструмент для создания mcp-серверов в 1с:предприятие путем разработки расширения конфигурации. позволяет интегрировать данные и функциональность 1с с ai-ассистентами (claude, cursor и т.д.). включает...

Инструмент для создания MCP-серверов в 1С:Предприятие путем разработки расширения конфигурации. Позволяет интегрировать данные и функциональность 1С с AI-ассистентами (Claude, Cursor и т.д.). Включает Python-прокси и пример расширения 1С с готовыми и

This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Инструмент для создания MCP-серверов в 1С:Предприятие путем

Use Cases

1C:Enterprise integration
Russian ERP system control
AI-assisted configuration
vladimir-kharin

Maintainer

LicenseMIT
Language1c enterprise
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx 1c

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use 1C MCP

The 1C MCP Server enables AI assistants like Claude and Cursor to integrate directly with 1C:Enterprise — the dominant ERP and business platform across Russia and the CIS region. By deploying a 1C configuration extension and publishing an HTTP service, developers expose business data and custom tools to any MCP-compatible AI client. This is the primary solution for teams that need AI-assisted querying, reporting, or automation inside their existing 1C:Enterprise environment without leaving the platform's BSL ecosystem.

Prerequisites

  • 1C:Enterprise platform (version 8.3+ recommended) with a web server configured for HTTP service publication
  • Python 3.8+ installed if using the Python proxy for OAuth2 authentication
  • Docker (optional) for containerized proxy deployment
  • An MCP-compatible client such as Claude Desktop or Cursor
  • Basic knowledge of 1C BSL (1C scripting language) to create custom tool handlers
1

Deploy the 1C Configuration Extension

Download or build the extension file from the repository's build directory and attach it to your 1C:Enterprise configuration. The extension adds the MCP subsystem, HTTP service, and example tool handlers to your existing database.

# The extension file is located at:
# build/MCP_Сервер.cfe
# Attach via: Configuration → Extensions → Add from file
2

Publish the HTTP Service on Your Web Server

In 1C:Enterprise Configurator, publish the mcp_APIBackend HTTP service to your web server (Apache or IIS). The resulting endpoint URL will follow the pattern shown below. Case sensitivity in the database name is critical — the URL path must exactly match the publication name.

# Published endpoint pattern:
http://<your-server>/<base>/hs/mcp/

# Example:
http://localhost/accounting/hs/mcp/
3

Configure Docker Proxy (Optional)

If your 1C server requires authentication or you want OAuth2 support, use the Python proxy included in the repository. Copy the example env file, fill in your credentials, and start the container.

cp .env.docker.example .env
# Edit .env and set:
# MCP_ONEC_URL=http://host.docker.internal/<base>/hs/mcp/
# ONEC_LOGIN=your_username
# ONEC_PASSWORD=your_password

docker compose up -d
4

Add a Custom Tool Handler in BSL

Create your own tools by adding a handler module to the mcp_КонтейнерыИнструментов subsystem. Each handler must implement two export methods: ДобавитьИнструменты() to describe the tool schema, and ВыполнитьИнструмент() to execute the logic.

// Example BSL structure (module in the subsystem):
// Export method 1 - Describe tools
Процедура ДобавитьИнструменты(Инструменты) Экспорт
    Инструмент = Инструменты.Добавить();
    Инструмент.Имя = "get_sales_report";
    Инструмент.Описание = "Returns sales report for a given period";
КонецПроцедуры

// Export method 2 - Execute tool
Функция ВыполнитьИнструмент(ИмяИнструмента, Параметры) Экспорт
    // Your BSL logic here
КонецФункции
5

Configure Your MCP Client

Point your MCP client to the published endpoint. For Claude Desktop, add the server configuration to your claude_desktop_config.json. The mcpServers block should reference the HTTP endpoint.

{
  "mcpServers": {
    "1c": {
      "command": "python",
      "args": ["proxy.py"],
      "env": {
        "MCP_ONEC_URL": "http://localhost/accounting/hs/mcp/",
        "ONEC_LOGIN": "your_username",
        "ONEC_PASSWORD": "your_password"
      }
    }
  }
}

1C MCP Examples

Client configuration

Claude Desktop configuration connecting to a locally-published 1C:Enterprise HTTP service via the Python proxy.

{
  "mcpServers": {
    "1c": {
      "command": "python",
      "args": ["proxy.py"],
      "env": {
        "MCP_ONEC_URL": "http://host.docker.internal/accounting/hs/mcp/",
        "ONEC_LOGIN": "admin",
        "ONEC_PASSWORD": "secret"
      }
    }
  }
}

Prompts to try

Example natural language prompts to use once the 1C MCP server is connected to your AI client.

- "Show me the sales totals for January 2025 from the accounting database"
- "List all open purchase orders in the system"
- "What inventory items are below their reorder threshold?"
- "Generate a balance sheet summary for Q4 2024"

Troubleshooting 1C MCP

POST requests are being converted to GET requests, returning errors

The database name in your URL must exactly match the publication name in 1C, including case. For example, use 'accounting' not 'Accounting'. Case mismatches cause HTTP redirects that convert POST to GET.

The MCP client cannot reach the 1C HTTP service from Docker

When 1C is running on the host machine and the proxy runs in Docker, set MCP_ONEC_URL to use 'host.docker.internal' instead of 'localhost' (e.g., http://host.docker.internal/accounting/hs/mcp/).

Authentication errors when connecting to the 1C database

Direct publication without authentication is required for the basic setup, which may be a security concern in production. Use the Python proxy with OAuth2 support for secure credential management.

Frequently Asked Questions about 1C MCP

What is 1C MCP?

1C MCP is a Model Context Protocol (MCP) server that инструмент для создания mcp-серверов в 1с:предприятие путем разработки расширения конфигурации. позволяет интегрировать данные и функциональность 1с с ai-ассистентами (claude, cursor и т.д.). включает python-прокси и пример расширения 1с с готовыми и It connects AI assistants to external tools and data sources through a standardized interface.

How do I install 1C MCP?

Follow the installation instructions on the 1C MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with 1C MCP?

1C MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is 1C MCP free to use?

Yes, 1C MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

1C MCP Alternatives — Similar Business Applications Servers

Looking for alternatives to 1C MCP? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.

n8n

189.1k

A comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou

LobeHub

77.5k

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Jeecgboot

46.4k

AI 低代码平台,「低代码 + 零代码」双模式驱动:低代码一键生成前后端代码,零代码 5 分钟搭建系统,AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等,兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式,消除 Java 项目 80% 的重复工作,提效而不失灵活。

CowAgent

44.7k

CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。

Minds Platform

39.2k

Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.

Astrbot

32.8k

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Browse More Business Applications MCP Servers

Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "1c": { "command": "npx", "args": ["-y", "1c"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use 1C MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides