gomcptest: Proof of Concept for MCP with Custom Host
A proof-of-concept demonstrating a custom-built host implementing an OpenAI-compatible API with Google Vertex AI, function calling, and interaction with MCP servers.
what is gomcptest?
gomcptest is a proof-of-concept project that demonstrates the implementation of a Model Context Protocol (MCP) with a custom-built host that is compatible with OpenAI's API and integrates Google Gemini.
how to use gomcptest?
To use gomcptest, clone the repository, navigate to the host/openaiserver directory, set the required environment variables, and run the server using Go.
key features of gomcptest?
- OpenAI Compatibility: Mimics the OpenAI v1 chat completion format.
- Google Gemini Integration: Utilizes VertexAI API for interaction with Gemini models.
- Streaming Support: Supports streaming responses from the server.
- Function Calling: Allows external function calls to be incorporated into chat responses.
- MCP Server Interaction: Demonstrates interaction with a hypothetical MCP server.
use cases of gomcptest?
- Testing and developing applications that require OpenAI-compatible APIs.
- Integrating Google Gemini models into custom applications.
- Exploring the functionalities of Model Context Protocols in AI applications.
FAQ from gomcptest?
- Is gomcptest suitable for production use?
No, gomcptest is a proof-of-concept and is not intended for production environments.
- What are the prerequisites for running gomcptest?
You need to have Go installed and configured, along with the necessary environment variables set.
- Can I modify the code?
Yes, the code is provided for educational purposes and can be modified as needed.
what is gomcptest?
gomcptest is a proof-of-concept project that demonstrates the implementation of a Model Context Protocol (MCP) with a custom-built host that is compatible with OpenAI's API and integrates Google Gemini.
how to use gomcptest?
To use gomcptest, clone the repository, navigate to the host/openaiserver directory, set the required environment variables, and run the server using Go.
key features of gomcptest?
- OpenAI Compatibility: Mimics the OpenAI v1 chat completion format.
- Google Gemini Integration: Utilizes VertexAI API for interaction with Gemini models.
- Streaming Support: Supports streaming responses from the server.
- Function Calling: Allows external function calls to be incorporated into chat responses.
- MCP Server Interaction: Demonstrates interaction with a hypothetical MCP server.
use cases of gomcptest?
- Testing and developing applications that require OpenAI-compatible APIs.
- Integrating Google Gemini models into custom applications.
- Exploring the functionalities of Model Context Protocols in AI applications.
FAQ from gomcptest?
- Is gomcptest suitable for production use?
No, gomcptest is a proof-of-concept and is not intended for production environments.
- What are the prerequisites for running gomcptest?
You need to have Go installed and configured, along with the necessary environment variables set.
- Can I modify the code?
Yes, the code is provided for educational purposes and can be modified as needed.