MCP Openai Complete

An OpenAI text completion service based on the MCP protocol that provides a standardized text generation interface for LLMs and supports asynchronous processing and request cancellation functions.

Artificial intelligence chatbots Developer tools #Text completion #MCP protocol #OpenAI #Asynchronous processing Local .TypeScript

rating : 2 points

downloads : 17

update time : 2025-04-28

What is the OpenAI Complete MCP Server?

This is a server based on the Model Context Protocol (MCP) that specifically provides text completion functionality for large language models (LLMs). It acts as an intermediate layer between LLM clients and any OpenAI-compatible API, making it particularly suitable for use with base models.

How to use the OpenAI Complete MCP Server?

You can start the server via a simple command line. After configuring the necessary API keys and model parameters, you can interact with the server through the MCP protocol to obtain text completion results.

Use cases

It is most suitable for application scenarios that require the text completion capabilities of base models, such as automatic text generation, code completion, and content expansion. Chat conversation scenarios are not supported.

Main features

Text completionProvides a single 'complete' tool for generating text completion results

Asynchronous processingSupports asynchronous processing of requests to avoid blocking the main thread

Timeout handlingImplements a timeout mechanism and provides graceful fallback handling

Request cancellationSupports canceling ongoing requests

Advantages and limitations

Advantages

Simple and easy-to-use interface design

Seamless integration with OpenAI-compatible APIs

Supports configuration of multiple generation parameters

Stable asynchronous processing mechanism

Limitations

Only supports text completion functionality and does not support chat conversations

Requires reliance on external API services

Base models may not be as accurate as fine-tuned models

How to use

Install dependencies

Use pnpm to install the project's required dependencies

Configure environment variables

Set the necessary API keys and model parameters

Start the server

Run the start command to start the service

Deploy using Docker (optional)

Build and run a Docker container

Usage examples

Basic text completionObtain the automatic completion result of a piece of text

Creative writingUse different temperature parameters to obtain more creative results

Technical document generationGenerate a technical description of an API document

Frequently asked questions

Which models does this server support?

How to set the length of the generated result?

Why did my request time out?

Does it support streaming responses?

Related resources

MCP protocol documentation

Official documentation for the Model Context Protocol

OpenAI API reference

Official reference documentation for the OpenAI API

GitHub repository

Project source code repository

🚀 OpenAI Completion MCP Server

An MCP (Model Context Protocol) based server that provides a clean interface for large language models to use text completion features. It communicates with any OpenAI-compatible API via the MCP protocol. This server acts as a bridge between LLM clients and arbitrary OpenAI-compatible APIs. The primary use case is for foundation models as the server does not support chat completion.

🚀 Quick Start

The OpenAI Completion MCP Server is a crucial component for enabling text completion features in large language models. It offers a seamless way to interact with OpenAI-compatible APIs through the MCP protocol.

✨ Features

Offers a single tool named "complete" for generating text completions.
Properly handles asynchronous processing to avoid blocking.
Implements timeout handling and graceful fallback.
Supports cancellation of ongoing requests.

📦 Installation

# Clone the repository
git clone <repository-url>
cd mcp-openai-complete

# Install dependencies
pnpm install

# Build the project
pnpm run build

🛠️ Configuration

The following environment variables are required:

OPENAI_API_KEY=Your Hyperbolic API key
OPENAI_API_BASE=https://api.hyperbolic.xyz/v1
OPENAI_MODEL=meta-llama/Meta-Llama-3.1-405B

💻 Usage Examples

Basic Usage

Start the server:

pnpm start

This will start the server on standard input/output, making it available for MCP clients to communicate with.

Docker Usage

Build the Docker image

docker build -t mcp-openai-complete .

Run the container

# Run with environment variables
docker run -it --rm \
  -e OPENAI_API_KEY="Your API key" \
  -e OPENAI_MODEL="gpt-3.5-turbo-instruct" \
  mcp-openai-complete

You can also use a .env file:

# Run using a .env file
docker run -it --rm \
  --env-file .env \
  mcp-openai-complete

Parameters for the "complete" tool

prompt (string, required): The text prompt to complete.
max_tokens (integer, optional): The maximum number of tokens to generate. Default: 150.
temperature (number, optional): Controls randomness (0 - 1). Default: 0.7.
top_p (number, optional): Controls diversity through nucleus sampling. Default: 1.0.
frequency_penalty (number, optional): Reduces the likelihood of repeating token sequences. Default: 0.0.
presence_penalty (number, optional): Increases the likelihood of talking about new topics. Default: 0.0.