Just Prompt is a lightweight 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. It allows you to easily interact with multiple models through a standardized set of tools.
# Clone the repository
git clone https://github.com/yourusername/just-prompt.git
cd just-prompt
# Install with pip
uv sync
Create a .env file with your API keys:
cp .env.sample .env
Then edit the .env file to add your API keys:
OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
GEMINI_API_KEY=your_gemini_api_key_here
GROQ_API_KEY=your_groq_api_key_here
DEEPSEEK_API_KEY=your_deepseek_api_key_here
OLLAMA_HOST=http://localhost:11434
mcp add-jsonTo add Just Prompt to Claude Code, run this command in Claude Code (replace the directory path as needed):
claude mcp add just-prompt "$(pbpaste)"
JSON configurations to copy:
Basic configuration:
{
"command": "uv",
"args": ["--directory", ".", "run", "just-prompt"]
}
With a custom default model:
{
"command": "uv",
"args": ["--directory", ".", "run", "just-prompt", "--default-models", "openai:gpt-4o"]
}
With multiple default models:
{
"command": "uv",
"args": ["--directory", ".", "run", "just-prompt", "--default-models", "openai:o3:high,openai:o4-mini:high,anthropic:claude-3-7-sonnet-20250219:4k,gemini:gemini-2.5-pro-preview-03-25,gemini:gemini-2.5-flash-preview-04-17"]
}
mcp add with project scope# With default models
claude mcp add just-prompt -s project \
-- \
uv --directory . \
run just-prompt
# With custom default model
claude mcp add just-prompt -s project \
-- \
uv --directory . \
run just-prompt --default-models "openai:gpt-4o"
# With multiple default models
claude mcp add just-prompt -s user \
-- \
uv --directory . \
run just-prompt --default-models "openai:o3:high,openai:o4-mini:high,anthropic:claude-3-7-sonnet-20250219:4k,gemini:gemini-2.5-pro-preview-03-25,gemini:gemini-2.5-flash-preview-04-17:4k"
claude mcp remove just-prompt
list_providers: Lists all available LLM providers
# Example usage
claude mcp list_providers
list_models: Lists all available models for a specific LLM provider
# Example usage
claude mcp list_models provider=openai
# Or using the short prefix
claude mcp list_models provider=o
prompt: Sends a prompt to multiple LLM models
# Example usage
claude mcp prompt text="Explain quantum computing in simple terms" models_prefixed_by_provider="openai:gpt-4o,anthropic:claude-3-5-haiku"
prompt_from_file: Sends a prompt from a file to multiple LLM models
# Example usage
claude mcp prompt_from_file file="./prompts/my_prompt.txt" models_prefixed_by_provider="openai:gpt-4o,anthropic:claude-3-5-haiku"
prompt_from_file_to_file: Sends a prompt from a file to multiple LLM models and saves responses as markdown files
# Example usage
claude mcp prompt_from_file_to_file file="./prompts/my_prompt.txt" models_prefixed_by_provider="openai:gpt-4o,anthropic:claude-3-5-haiku" output_dir="./responses"
ceo_and_board: Sends a prompt to multiple 'board member' models and has a 'CEO' model make a decision based on their responses
# Example usage
claude mcp ceo_and_board file="./prompts/decision_prompt.txt" models_prefixed_by_provider="openai:gpt-4o,anthropic:claude-3-5-haiku,gemini:gemini-2.5-pro-exp-03-25" output_dir="./decisions" ceo_model="openai:o3"
When specifying models, you must use provider prefixes. Both full names and short forms are supported:
o or openai (e.g., o:gpt-4o-mini or openai:gpt-4o-mini)a or anthropic (e.g., a:claude-3-5-haiku or anthropic:claude-3-5-haiku)g or gemini (e.g., g:gemini-2.5-pro-exp-03-25 or gemini:gemini-2.5-pro-exp-03-25)q or groq (e.g., q:llama-3.1-70b-versatile or groq:llama-3.1-70b-versatile)d or deepseek (e.g., d:deepseek-coder or deepseek:deepseek-coder)l or ollama (e.g., l:llama3.1 or ollama:llama3.1)For OpenAI o-series models, you can control reasoning effort by adding a suffix:
:low - minimal internal reasoning (faster, cheaper):medium - balanced (default):high - thorough reasoning (slower, more tokens)Examples:
openai:o4-mini:low
o:o4-mini:high
For Claude 3.7 Sonnet, you can enable thinking tokens with a suffix:
anthropic:claude-3-7-sonnet-20250219:1k # 1024 thinking tokens
anthropic:claude-3-7-sonnet-20250219:4k # 4096 thinking tokens
anthropic:claude-3-7-sonnet-20250219:8000 # 8000 thinking tokens
For Gemini 2.5 Flash, you can enable thinking budget with a suffix:
gemini:gemini-2.5-flash-preview-04-17:1k # 1024 thinking budget
gemini:gemini-2.5-flash-preview-04-17:4k # 4096 thinking budget
gemini:gemini-2.5-flash-preview-04-17:8000 # 8000 thinking budget
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.