Spring MCP 1c Copilot

🚀 Spring Boot MCP Server for 1C: Copilot

A fully functional MCP (Model Context Protocol) server for integrating with the 1C: Copilot API

📄 License: Open Source for personal and non - commercial use. Commercial use requires permission from the author.

✨ Features

• 🎯 MCP Protocol Support: Full support for the MCP protocol for integration with AI assistants.
• 🤖 1C: Copilot Integration: Direct integration with the 1C: Copilot API through proper endpoints.
• ⚡ SSE Support: Support for Server - Sent Events for real - time communication.
• 🌐 REST API: Additional REST endpoints for direct interaction.
• 📚 Swagger UI: Interactive API documentation.
• 🐳 Docker Ready: Ready - to - use Docker configurations for deployment.
• 🔐 Authorization: Support for Bearer tokens for the 1C: Copilot API.

🛠️ MCP Tools

1. ask_1c_ai

Ask a question to the 1C: Copilot AI.

• question (required): The question for the AI.
• programming_language (optional): The programming language.
• create_new_session (optional): Create a new session.

2. explain_1c_syntax

Explain the syntax of a 1C element.

• syntax_element (required): The syntax element to be explained.
• context (optional): The usage context.

3. check_1c_code

Check 1C code for errors.

• code (required): The 1C code to be checked.
• check_type (optional): The type of check (syntax, logic, performance).

🚀 Quick Start

Requirements

• Java 17+
• Docker (recommended)
• Access token for the 1C: Copilot API

1. Obtaining the 1C: Copilot Token

1. Register at code.1c.ai.
2. Obtain the access token in your personal account.
3. Save the token for use in environment variables.

2. Local Deployment

# Clone the repository
git clone <repository-url>
cd spring-mcp-1c-copilot

# Set environment variables
export ONEC_AI_TOKEN="your_token_here"
export ONEC_AI_BASE_URL="https://code.1c.ai"

# Run the application
./gradlew bootRun

3. Docker Deployment (Recommended)

# Build the image
docker build -f Dockerfile.build -t spring-mcp-1c-copilot .

# Run the container
docker run -d --name spring-mcp-1c-copilot -p 8000:8000 \
  -e ONEC_AI_TOKEN="your_token_here" \
  spring-mcp-1c-copilot

📡 API Endpoints

MCP Endpoints

• POST /mcp - The main MCP endpoint for JSON - RPC requests.
• GET /mcp - SSE stream for MCP clients.

REST API Endpoints

• POST /api/ask-ai - Ask a question to the 1C: Copilot AI.
• POST /api/explain-syntax - Explain the 1C syntax.
• POST /api/check-code - Check 1C code for errors.
• GET /api/health - Check the server status.

Documentation

• http://localhost:8000/swagger-ui.html - Swagger UI documentation.
• http://localhost:8000/api-docs - OpenAPI JSON schema.

⚙️ Configuration

Environment Variables

application.yml

onec:
  ai:
    token: ${ONEC_AI_TOKEN:}
    base-url: ${ONEC_AI_BASE_URL:https://code.1c.ai}
    timeout: ${ONEC_AI_TIMEOUT:30}

server:
  port: ${SSE_PORT:8000}

springdoc:
  api-docs:
    path: /api-docs
  swagger-ui:
    path: /swagger-ui.html
    enabled: true

🔗 Integration with Cursor IDE

Add the following to ~/.cursor/mcp.json:

{
  "servers": {
    "1c-copilot-proxy": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

After that, all tools for working with 1C: Copilot will be available in Cursor IDE!

🏗️ Project Structure

src/main/kotlin/ru/alkoleft/copilot/
├── McpCopilotApplication.kt          # Main application class
├── config/
│   ├── McpConfiguration.kt           # MCP configuration
│   └── OpenApiConfig.kt              # Swagger configuration
├── controller/
│   ├── McpController.kt              # MCP controller
│   └── RestApiController.kt          # REST API controller
└── service/
    ├── OneCApiClient.kt              # Client for the 1C: Copilot API
    └── OneCCopilotService.kt         # Service with MCP tools

🧪 Testing

MCP Initialization Test

curl -X POST http://localhost:8000/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": "1",
    "method": "initialize",
    "params": {
      "protocolVersion": "2025-06-18",
      "capabilities": {"tools": true}
    }
  }'

REST API Test

curl -X POST "http://localhost:8000/api/ask-ai?question=How to create a directory in 1C?"

🔧 Development

Build

./gradlew build

Run Tests

./gradlew test

Local Development

./gradlew bootRun --args='--spring.profiles.active=dev'

📋 Logging and Debugging

View Docker Container Logs

docker logs spring-mcp-1c-copilot --follow

Logging Levels

• DEBUG - Detailed logs for development.
• INFO - Main events (default).
• WARN - Warnings.
• ERROR - Errors.

🚀 Production Deployment

See DEPLOYMENT.md for a detailed guide on server deployment.

🙏 Acknowledgments

This project is based on the work of the following repositories:

• artesk/1copilot_MCP - The original MCP server for 1C: Copilot in Python.
• rentgengl/copilot-1c-proxy - A proxy server for requests to 1C: Copilot.

Huge thanks to the authors of these projects! 🎉

Our Spring Boot MCP Server builds on the ideas of these projects by adding:

• A modern architecture using Spring Boot and Kotlin.
• Full support for the MCP protocol with SSE.
• Swagger UI documentation.
• Ready - to - use production configurations.
• Deployment automation.

🤝 Contributing

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add amazing feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a Pull Request.

📄 License

License: Open Source (Personal and Non - Commercial Use)

• ✅ Personal Use - Free.
• ✅ Non - Commercial Use - Free.
• ✅ Educational Purposes - Free.
• ❌ Commercial Use - Only with permission from the author.

Contact the author for permission to use commercially.

Based Projects:

• artesk/1copilot_MCP - Unlicense
• rentgengl/copilot-1c-proxy - MIT License

🆘 Support

If you encounter problems:

1. Check Issues.
2. Ensure that your 1C: Copilot token is valid.
3. Check the container logs: docker logs spring-mcp-1c-copilot.
4. Create a new Issue with a detailed description of the problem.

🎉 Enjoy working with 1C: Copilot via MCP!