MCP Context SDK

Overview

The MCP Context SDK is a modular, production-ready Python SDK that enables AI agents, models, and tools to work with structured context schemas. It provides a standardized way to handle context in AI applications, making it easier to build, validate, and share context-aware AI systems.

Features

• 🎯 Dynamic Context Construction: Build and validate context dynamically using JSON schemas
• 🔄 Schema-to-Prompt Conversion: Convert structured schemas into natural language prompts
• 🛠️ Framework Integrations:
  • FastAPI for web applications
  • LangChain for AI workflows
  • AutoGen for multi-agent systems
  • CrewAI for team-based AI operations
  • LangGraph for complex AI workflows
  • OpenDevin for development automation
• 📝 CLI Tools: Command-line interface for schema management and context conversion
• 🎨 Streamlit UI: Interactive web interface for context editing and preview
• ✨ Type Safety: Full type hints and schema validations
• 📚 Documentation: Comprehensive guides and API references

Installation

From PyPI

pip install mcp-context-sdk

From Source

# Clone the repository
git clone https://github.com/ankit-gautam23/mcp-context-sdk.git
cd mcp-context-sdk

# Install with Poetry
poetry install

# Or install with pip
pip install -e .

Optional Dependencies

Install additional dependencies for specific integrations:

# FastAPI integration
pip install "mcp-context-sdk[fastapi]"

# All integrations
pip install "mcp-context-sdk[all]"

Quick Start

Basic Usage

from mcp_context_sdk import ContextBuilder, SchemaLoader

# Load a schema
schema = SchemaLoader().load_schema("coding", version="v1")

# Create context
context = ContextBuilder(schema).build({
    "language": "python",
    "task_type": "development",
    "complexity": "intermediate"
})

# Convert to prompt
prompt = context.to_prompt()

CLI Usage

List available schemas:

mcp list-schemas coding

Convert context to prompt:

mcp convert-context context.json coding --version v1

Streamlit UI

Run the interactive UI:

streamlit run examples/streamlit_ui.py

Documentation

Visit our documentation site for:

• 📖 User Guide - Get started with MCP Context SDK
• 📚 API Reference - Detailed API documentation
• 🚀 Examples - Code examples and tutorials
• 🤝 Contributing Guide - How to contribute to the project
• 📋 Code of Conduct - Community guidelines
• 🔒 Security Policy - Security reporting guidelines

Development

Setup Development Environment

1. Clone the repository:

   git clone https://github.com/ankit-gautam23/mcp-context-sdk.git
   cd mcp-context-sdk
   

2. Install development dependencies:

   poetry install
   

3. Run tests:

   poetry run pytest
   

4. Run linting:

   poetry run black .
   poetry run isort .
   poetry run flake8
   

Project Structure

mcp-context-sdk/
├── mcp_context_sdk/      # Main package
│   ├── core/            # Core functionality
│   ├── integrations/    # Framework integrations
│   └── utils/           # Utility functions
├── docs/                # Documentation
│   ├── landing/        # GitHub Pages site
│   └── api/            # API documentation
├── examples/            # Example code
├── schemas/             # JSON schemas
└── tests/              # Test suite

Contributing

We welcome contributions! Please see our Contributing Guide for details on:

• How to submit issues
• How to submit pull requests
• Our development workflow
• Code style guidelines

Security

Please report any security issues to SECURITY.md.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you use MCP Context SDK in your research, please cite:

@software{mcp_context_sdk,
  author = {Ankit Gautam},
  title = {MCP Context SDK},
  year = {2025},
  url = {https://github.com/ankit-gautam23/mcp-context-sdk}
}

Contact

• GitHub Issues: Create an issue
• Email: ankit.gautamp23@gmail.com

Acknowledgments

• Thanks to all contributors who have helped shape this project
• Inspired by various AI frameworks and context management systems