Happy slice of mcp pizzaMCP.pizza
just-prompt

just-prompt

MCP.Pizza Chef: disler

Instead of opening four different chat windows, this sends one question to OpenAI, Anthropic, Google Gemini, Groq, DeepSeek and locally run Ollama models at once, then hands back every reply. A board-and-chief-executive mode goes further: several models weigh in like advisors, and one model you nominate reads their answers and makes the call. Replies can be saved as files. You supply your own paid keys for whichever providers you want, and any you skip are simply listed as unavailable.

Unmaintained · No commits in 12 months.
Other
Writing

Use This MCP server To

Ask three models the same question and compare answers Get a second opinion before I commit to a plan Have several models debate a hard decision for me Send a long prompt from a file to every model Save each model's answer as its own document Check which providers my keys currently unlock

README

Just Prompt - A lightweight MCP server for LLM providers

just-prompt is a Model Control Protocol (MCP) server that provides a unified interface to various Large Language Model (LLM) providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama. See how we use the ceo_and_board tool to make hard decisions easy with o3 here.

Just Prompt Logo

Just Prompt Logo

Tools

The following MCP tools are available in the server:

  • prompt: Send a prompt to multiple LLM models

    • Parameters:
      • text: The prompt text
      • models_prefixed_by_provider (optional): List of models with provider prefixes. If not provided, uses default models.

  • prompt_from_file: Send a prompt from a file to multiple LLM models

    • Parameters:
      • abs_file_path: Absolute path to the file containing the prompt (must be an absolute path, not relative)
      • models_prefixed_by_provider (optional): List of models with provider prefixes. If not provided, uses default models.

  • prompt_from_file_to_file: Send a prompt from a file to multiple LLM models and save responses as markdown files

    • Parameters:
      • abs_file_path: Absolute path to the file containing the prompt (must be an absolute path, not relative)
      • models_prefixed_by_provider (optional): List of models with provider prefixes. If not provided, uses default models.
      • abs_output_dir (default: "."): Absolute directory path to save the response markdown files to (must be an absolute path, not relative)

  • ceo_and_board: Send a prompt to multiple 'board member' models and have a 'CEO' model make a decision based on their responses

    • Parameters:
      • abs_file_path: Absolute path to the file containing the prompt (must be an absolute path, not relative)
      • models_prefixed_by_provider (optional): List of models with provider prefixes to act as board members. If not provided, uses default models.
      • abs_output_dir (default: "."): Absolute directory path to save the response files and CEO decision (must be an absolute path, not relative)
      • ceo_model (default: "openai:o3"): Model to use for the CEO decision in format "provider:model"

  • list_providers: List all available LLM providers

    • Parameters: None

  • list_models: List all available models for a specific LLM provider

    • Parameters:
      • provider: Provider to list models for (e.g., 'openai' or 'o')

Provider Prefixes

every model must be prefixed with the provider name

use the short name for faster referencing

  • o or openai: OpenAI
    • o:gpt-4o-mini
    • openai:gpt-4o-mini
  • a or anthropic: Anthropic
    • a:claude-3-5-haiku
    • anthropic:claude-3-5-haiku
  • g or gemini: Google Gemini
    • g:gemini-2.5-pro-exp-03-25
    • gemini:gemini-2.5-pro-exp-03-25
  • q or groq: Groq
    • q:llama-3.1-70b-versatile
    • groq:llama-3.1-70b-versatile
  • d or deepseek: DeepSeek
    • d:deepseek-coder
    • deepseek:deepseek-coder
  • l or ollama: Ollama
    • l:llama3.1
    • ollama:llama3.1

just-prompt FAQ

Do I need paid accounts?
Yes, for the paid providers. You add your own keys, and any provider you leave out is simply listed as unavailable.
Can I use this to compare answers from different models?
Yes, that is its whole point. One question goes out and every reply comes back together.
Can it use models running on my own computer?
Yes. Local models through Ollama are supported alongside the paid services.
Which apps does it work in?
The readme documents Claude Code, and the same configuration pattern works in other apps that accept MCP servers.
What is the board-and-chief-executive feature?
Several models answer as advisors, then one model you nominate reads all of them and gives a final decision.
How hard is setup?
Moderate. You copy a small configuration snippet and add your keys to a file. No coding is required.