mcp-server
If you are the rightful owner of mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A simple server implementation for the Model Context Protocol that provides a unified API for multiple AI model providers.
The Model Context Protocol (MCP) Server is designed to offer a unified API for interacting with multiple AI model providers such as Anthropic and OpenAI. It supports both chat completions and legacy completions, allowing for seamless integration with various AI models. The server is equipped with tool calling support, context/system message handling, and environment-based configuration. It uses MongoDB for persistence and state management, ensuring that tool execution history and analytics are maintained effectively. The server is highly configurable and can be set up using environment variables, making it adaptable to different deployment scenarios. Additionally, it provides a comprehensive set of API endpoints for interacting with AI models and managing tools, making it a versatile solution for developers looking to integrate AI capabilities into their applications.
Features
- Unified API for multiple AI providers (Anthropic, OpenAI)
- Support for chat completions and legacy completions
- Tool calling support
- Context/system message handling
- Environment-based configuration
