Just Prompt

v1.0.0Coding Agentsstable

A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.

just-promptmcpai-integration
Share:
730
Stars
0
Downloads
0
Weekly
0/5

What is Just Prompt?

Just Prompt is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to lightweight mcp server that provides a unified interface to various llm providers including openai, anthropic, google gemini, groq, deepseek, and ollama.

A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A lightweight MCP server that provides a unified interface t

Use Cases

Unify access to OpenAI, Anthropic, Google Gemini, Groq, and DeepSeek.
Switch between LLM providers through a single MCP interface.
disler

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx just-prompt

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Just Prompt

Just Prompt is a lightweight MCP server that exposes a unified interface for sending prompts to multiple LLM providers — OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama — from a single tool call inside any MCP-compatible client. Beyond simple prompt forwarding, it includes a 'ceo_and_board' pattern where one model acts as the decision-maker after receiving input from several 'board member' models, making multi-model reasoning workflows easy to build. Developers use it to compare model outputs, run parallel reasoning experiments, and automate decisions that benefit from consulting multiple AI perspectives.

Prerequisites

  • Python 3.10+ and uv package manager installed
  • API keys for each provider you intend to use: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, DEEPSEEK_API_KEY
  • Ollama running locally at http://localhost:11434 if using local models
  • An MCP client such as Claude Code or Claude Desktop
  • Git to clone the repository
1

Clone the repository and install dependencies

Clone the just-prompt repo and install Python dependencies using uv.

git clone https://github.com/disler/just-prompt.git
cd just-prompt
uv sync
2

Create a .env file with your API keys

Copy the example env file and fill in keys for the providers you want to use. You only need keys for providers you plan to query.

cp .env.example .env
# Edit .env and add:
# OPENAI_API_KEY=sk-...
# ANTHROPIC_API_KEY=sk-ant-...
# GEMINI_API_KEY=AIza...
# GROQ_API_KEY=gsk_...
# DEEPSEEK_API_KEY=sk-...
# OLLAMA_HOST=http://localhost:11434
3

Add the server to Claude Code

Register just-prompt as an MCP server scoped to your current project using the Claude Code CLI.

claude mcp add just-prompt -s project -- uv --directory /path/to/just-prompt run just-prompt
4

Verify available providers and models

Ask Claude to list the available providers and models by calling the list_providers and list_models tools to confirm configuration is correct.

5

Configure Claude Desktop (alternative)

Add the server to your Claude Desktop config, pointing uv to the cloned directory.

{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": ["--directory", "/path/to/just-prompt", "run", "just-prompt"],
      "env": {
        "OPENAI_API_KEY": "sk-your-key",
        "ANTHROPIC_API_KEY": "sk-ant-your-key",
        "GEMINI_API_KEY": "AIza-your-key"
      }
    }
  }
}

Just Prompt Examples

Client configuration

Claude Desktop configuration for just-prompt with multiple provider API keys.

{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": ["--directory", "/path/to/just-prompt", "run", "just-prompt"],
      "env": {
        "OPENAI_API_KEY": "sk-your-openai-key",
        "ANTHROPIC_API_KEY": "sk-ant-your-anthropic-key",
        "GEMINI_API_KEY": "AIza-your-gemini-key",
        "GROQ_API_KEY": "gsk_your-groq-key",
        "DEEPSEEK_API_KEY": "sk-your-deepseek-key",
        "OLLAMA_HOST": "http://localhost:11434"
      }
    }
  }
}

Prompts to try

Example prompts that use the unified multi-LLM interface and CEO/board decision pattern.

- "Send this prompt to gpt-4o and claude-3-5-sonnet and compare their answers: What are the main risks of microservices?"
- "Use the ceo_and_board tool: have o3 decide the best database for a startup based on input from gpt-4o and gemini-1.5-pro"
- "List all available models and their provider prefixes"
- "Send my prompt from context.txt to deepseek-r1 and save the response to output.md"
- "Prompt all configured providers with the same question and show me the differences in their responses"

Troubleshooting Just Prompt

Provider returns authentication error

Confirm the correct env var name is set in .env: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, DEEPSEEK_API_KEY. Restart the MCP server after editing .env.

Ollama models not listed

Ensure Ollama is running ('ollama serve') and OLLAMA_HOST is set to http://localhost:11434 (or your custom host). Pull a model first with 'ollama pull llama3'.

uv command not found when starting server

Install uv via 'curl -LsSf https://astral.sh/uv/install.sh | sh' and ensure it is on your PATH. Verify with 'uv --version'.

Frequently Asked Questions about Just Prompt

What is Just Prompt?

Just Prompt is a Model Context Protocol (MCP) server that lightweight mcp server that provides a unified interface to various llm providers including openai, anthropic, google gemini, groq, deepseek, and ollama. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Just Prompt?

Follow the installation instructions on the Just Prompt GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Just Prompt?

Just Prompt works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Just Prompt free to use?

Yes, Just Prompt is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "just-prompt": { "command": "npx", "args": ["-y", "just-prompt"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Just Prompt?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides