A lightweight MCP server providing a unified interface to multiple LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.
Just Prompt is a lightweight Model Control Protocol (MCP) server that provides a unified interface to multiple large language model providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama. It solves the problem of managing different APIs and authentication methods by offering a single, consistent way to interact with various AI models.
Developers and AI engineers who need to work with multiple LLM providers and want to avoid vendor lock-in or manage complex integration code.
Just Prompt offers a simple, unified API that abstracts away provider-specific complexities, supports parallel model execution, and includes unique features like the CEO & Board tool for collaborative AI decision-making.
just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Abstracts away provider-specific differences by offering a single interface for OpenAI, Anthropic, Gemini, Groq, DeepSeek, and Ollama, as evidenced by the consistent provider prefix system in the README.
Enables running multiple LLM models simultaneously from a single prompt, allowing for easy comparison and aggregation of responses across providers.
Supports sending prompts from text files and saving responses as markdown files, streamlining batch processing and documentation, as detailed in the prompt_from_file_to_file tool.
Integrates provider-specific features like OpenAI's reasoning effort levels, Claude's thinking tokens, and Gemini's thinking budgets through model name suffixes, enhancing model performance tuning.
Includes a unique tool to simulate a board of AI models with a CEO model making final decisions, useful for collaborative AI analysis and hard decision scenarios.
File-based tools mandate absolute file paths, not relative ones, which can be cumbersome and error-prone in dynamic or cross-platform development environments.
Requires setting up multiple environment variables for API keys, with missing keys disabling providers silently, complicating setup and error diagnosis.
Tied exclusively to the Model Control Protocol ecosystem, limiting usability outside MCP clients like Claude Code and offering no alternative interfaces or standalone APIs.
The README lacks details on robust error handling, retry mechanisms, or fallback strategies for API failures, which could be critical for production reliability.