# just-prompt MCP server [[Model Context Protocol (MCP)]] server that can be used to prompt different [[Large Language Models (LLMs)]] from the current one. It provides a unified interface for all supported models. It can also prompt multiple models in parallel. Supports [[OpenAI]]'s models, [[Anthropic]]'s [[30 Areas/33 Permanent notes/33.02 Content/Claude|Claude]], Google's [[Gemini]], [[xAI]]'s [[Grok]], [[Deepseek]], [[Ollama]], ... ## Tools This MCP server provides the following tools: - `prompt`: send a prompt to multiple LLMs - Parameters - `text` the prompt text - `models_prefixed_by_provider` (optional): list of models with provider prefixes. If not defined, uses default models - `prompt_from_file`: send a prompt from a file to multiple LLMs - Parameters - `abs_file_path`: absolute path to the file containing the prompt - `models_prefixed_by_provider` (optional): list of models with provider prefixes. If not defined, uses default models - `ceo_and_board`: prompt 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 - `models_prefixed_by_provider` (optional): list of models with provider prefixes. If not defined, uses default models - `abs_output_dir` (default: `'.'`): absolute directory path to save the response files and CEO decision - `ceo_model` (default: `openai:o3`): model to use for the CEO decision using format `provider:model` - `list_providers`: list available LLM providers - Parameters - None - `list_models`: list all available for a specific LLM provider - Parameters - `provider`: provider to list models for (e.g., `openai`) ## 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` ## Examples Using an input file: ``` prompts_from_file_to_file( from_file = foo.md, models = "openai:o3-mini, anthropic:claude-3-7-sonnet-20250219:4k, gemini-2.0-flash-thinking-exp", output_dir = bar/ ) ``` ## Configuration ``` "mcpServers": { "just-prompt": { "type": "stdio", "command": "uv", "args": [ "--directory", ".", "run", "just-prompt", "--default-models", "anthropic:claude-3-7-sonnet-20250219,openai:o3-mini,gemini:gemini-2.0-flash" ], "env": {} } } ``` ## References - Official website and source code: https://github.com/disler/just-prompt