OpenAI Complete MCP Server
@aiamblichus
MCP server for OpenAI text completion
Overview
What is OpenAI Complete MCP Server?
The OpenAI Complete MCP Server is an MCP server that provides a clean interface for LLMs to use text completion capabilities through the MCP protocol. It acts as a bridge between an LLM client and any OpenAI-compatible API. The primary use case is for base models, as it does not support chat completions.
How to use OpenAI Complete MCP Server?
Install by cloning the repository, installing dependencies with pnpm install, building with pnpm run build, and starting with pnpm start. Alternatively, use Docker: build the image and run the container with environment variables. The server exposes a single "complete" tool with parameters such as prompt (required), max_tokens, temperature, top_p, frequency_penalty, and presence_penalty.
Key features of OpenAI Complete MCP Server
- Provides a single "complete" tool for text completions.
- Handles asynchronous processing without blocking.
- Implements timeout handling with graceful fallbacks.
- Supports cancellation of ongoing requests.
- Works with any OpenAI-compatible API.
Use cases of OpenAI Complete MCP Server
- Using base models for text completion via MCP protocol.
- Integrating text completion capabilities into MCP-enabled clients.
- Leveraging OpenAI-compatible API endpoints for completions.
FAQ from OpenAI Complete MCP Server
What does this server do?
It bridges an LLM client to any OpenAI-compatible API for text completions, exposing a "complete" tool via MCP.
Does it support chat completions?
No, it only supports text completions (base models), not chat completions.
What are the required environment variables?
OPENAI_API_KEY, OPENAI_API_BASE, and OPENAI_MODEL are required.
