広告掲載
MCP.so
ログイン

Just Prompt - A lightweight MCP server for LLM providers

@disler

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

disler

Just Prompt - A lightweight MCP server for LLM providers について

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

Just Prompt - A lightweight MCP server for LLM providers の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Just Prompt - A lightweight MCP server for LLM providers のツール

6

Send a prompt to multiple LLM models

Send a prompt from a file to multiple LLM models

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

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

List all available LLM providers

List all available models for a specific LLM provider

概要

What is Just Prompt?

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. It is designed for developers and AI practitioners who need to query multiple models from different providers through a single API.

How to use Just Prompt?

Install by cloning the repository and running uv sync. Configure API keys in a .env file, then start the server with uv run just-prompt (optionally with --default-models). Use MCP tools such as prompt, prompt_from_file, prompt_from_file_to_file, ceo_and_board, list_providers, and list_models to send prompts, manage files, or list available options.

Key features of Just Prompt

  • Unified API for multiple LLM providers
  • Send prompts from strings or files
  • Run multiple models in parallel
  • Automatic model name correction
  • Save responses to markdown files
  • Easy listing of available providers and models
  • CEO-and-board decision flow using multiple models

Use cases of Just Prompt

  • Send the same prompt to several LLMs and compare outputs
  • Load a prompt from a file and query multiple models simultaneously
  • Use a board of models with a CEO model to synthesize decisions
  • List all available providers and models for configuration

よくある質問

1

Which LLM providers does Just Prompt support?

Just Prompt supports OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.

2

How do I configure API keys for Just Prompt?

Create a `.env` file with your API keys for the providers you wish to use, following the `.env.sample` template provided in the repository.

3

How can I control reasoning effort for OpenAI o‑series models?

Append `:low`, `:medium`, or `:high` to the model name (e.g., `openai:o4-mini:high`) to set the reasoning effort level.

4

How do I enable thinking tokens for Claude models?

Append a thinking budget suffix like `:1k` or `:4k` to the model name (e.g., `anthropic:claude-opus-4-20250514:4k`). Valid budgets range from 1024 to 16000 tokens.

5

How can I set thinking budget for Gemini models?

Append a budget suffix like `:1k` to the model name (e.g., `gemini:gemini-2.5-flash-preview-04-17:4k`). Valid budgets range from 0 to 24576.

コメント

「AI とエージェント」の他のコンテンツ

hausverbot

eliduarte37

BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2

AON — Agent Offer Network

AON

AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.

2

treg.to

Jason Zhou

OpenRouter for tools & data — 3,028 APIs for your agent, one token, pay per call. treg.to is a remote MCP server at https://treg.to/mcp/ that gives an agent 3,028 ready-to-call API endpoints across 82 platforms: SEO and

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

3
広告掲載