I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

MCP-Openai-Complete
Servidor MCP para finalización de texto de OpenAI
1
Github Watches
1
Github Forks
0
Github Stars
OpenAI Complete MCP Server
An MCP (Model Context Protocol) server that provides a clean interface for LLMs to use text completion capabilities through the MCP protocol. This server acts as a bridge between an LLM client and any OpenAI's compatible API. The primary use case is for base models, as the server does not provide support for chat completions.
Features
- Provides a single tool named "complete" for generating text completions
- Properly handles asynchronous processing to avoid blocking
- Implements timeout handling with graceful fallbacks
- 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
Start the server:
pnpm start
This will start the server on stdio, making it available for MCP clients to communicate with.
Docker Usage
Building the Docker Image
docker build -t mcp-openai-complete .
Running 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 with .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): Maximum tokens to generate, default: 150 -
temperature
(number, optional): Controls randomness (0-1), default: 0.7 -
top_p
(number, optional): Controls diversity via nucleus sampling, default: 1.0 -
frequency_penalty
(number, optional): Decreases repetition of token sequences, default: 0.0 -
presence_penalty
(number, optional): Increases likelihood of talking about new topics, default: 0.0
Development
For development with auto-reloading:
npm run dev
License
MIT
相关推荐
Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Descubra la colección más completa y actualizada de servidores MCP en el mercado. Este repositorio sirve como un centro centralizado, que ofrece un extenso catálogo de servidores MCP de código abierto y propietarios, completos con características, enlaces de documentación y colaboradores.
Manipulación basada en Micrypthon I2C del expansor GPIO de la serie MCP, derivada de AdaFruit_MCP230xx
Espejo dehttps: //github.com/agentience/practices_mcp_server
La aplicación AI de escritorio todo en uno y Docker con trapo incorporado, agentes de IA, creador de agentes sin código, compatibilidad de MCP y más.
Una puerta de enlace de API unificada para integrar múltiples API de explorador de blockchain similar a Esterscan con soporte de protocolo de contexto modelo (MCP) para asistentes de IA.
Reviews

user_VGmshbtF
I've been using mcp-openai-complete for a while now, and it has significantly enhanced my coding efficiency. The author, aiamblichus, has done a fantastic job in creating a straightforward and powerful tool. The integration with OpenAI is seamless, and the support for multiple languages ensures versatility in projects. Highly recommend checking it out on GitHub!