1. Home
  2. Servers
  3. AI Models & Agents
  4. Just Prompt

Server profile

Just Prompt MCP Server

Just Prompt lets an MCP assistant consult several language models and preserve their answers. Alongside parallel prompting, it offers a panel workflow in which a designated model makes a decision after reviewing other responses.

View repositoryInstall & configure

Server facts

Just Prompt MCP Server

Project

Author
disler
Repository
github.com/disler/just-prompt
License
Not specified
Category
AI Models & Agents

Tech

Runtime / language
pythonPython
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
739
Last commit
Data as of

Tags

  • Llm Routing
  • Model Comparison
  • Ollama
  • Parallel Prompts
  • Python

Overview

Just Prompt organizes model consultation into direct calls, file-based runs, and a decision-making panel. Direct calls accept prompt text, while the file tools read a prompt from an absolute path; one variant also writes each response as Markdown. The panel tool collects answers from designated board models, then passes them to a CEO model to make a decision and saves the outputs. Separate discovery operations expose providers and the models available for a chosen provider. Parallel execution lets a request consult several selected models rather than requiring sequential calls through separate integrations.

Provider support combines a local option, Ollama, with hosted services from DeepSeek, Groq, Google, Anthropic, and OpenAI. Model names identify their provider through a full prefix or a short alias. Configured defaults apply when a request does not choose models, and the first default model is also used to correct model names. Missing credentials do not block startup: the affected provider is reported unavailable, while configured providers remain usable. The README launches the Python project with uv from a local checkout after synchronizing dependencies. It also documents suffixes for model-specific reasoning settings: effort levels for certain OpenAI models, thinking tokens for supported Claude models, and a thinking budget for a specified Gemini model. These controls have distinct compatibility and budget rules, so they should not be treated as a universal setting across providers.

Install & configure

Requirements

  • Python and uv
  • Local checkout with dependencies prepared using uv sync
  • Credentials for chosen hosted providers, or an Ollama endpoint
Documented launch / install command
uv --directory . run just-prompt

This is the minimal README launch, not uv sync alone, which only prepares dependencies. The dot refers to the checkout directory; use the checkout's path if the client starts elsewhere. Provider values can be supplied by environment or .env. The optional --default-models argument chooses fallback models.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "just-prompt"
      ],
      "env": {
        "OPENAI_API_KEY": "<credential if selecting OpenAI models>",
        "ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
        "GEMINI_API_KEY": "<credential if selecting Gemini models>",
        "GROQ_API_KEY": "<credential if selecting Groq models>",
        "DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
        "OLLAMA_HOST": "<address of the Ollama instance to consult>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "just-prompt"
      ],
      "env": {
        "OPENAI_API_KEY": "<credential if selecting OpenAI models>",
        "ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
        "GEMINI_API_KEY": "<credential if selecting Gemini models>",
        "GROQ_API_KEY": "<credential if selecting Groq models>",
        "DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
        "OLLAMA_HOST": "<address of the Ollama instance to consult>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "just-prompt": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "just-prompt"
      ],
      "env": {
        "OPENAI_API_KEY": "<credential if selecting OpenAI models>",
        "ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
        "GEMINI_API_KEY": "<credential if selecting Gemini models>",
        "GROQ_API_KEY": "<credential if selecting Groq models>",
        "DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
        "OLLAMA_HOST": "<address of the Ollama instance to consult>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "just-prompt": {
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "just-prompt"
      ],
      "env": {
        "OPENAI_API_KEY": "<credential if selecting OpenAI models>",
        "ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
        "GEMINI_API_KEY": "<credential if selecting Gemini models>",
        "GROQ_API_KEY": "<credential if selecting Groq models>",
        "DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
        "OLLAMA_HOST": "<address of the Ollama instance to consult>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "just-prompt": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "just-prompt"
      ],
      "env": {
        "OPENAI_API_KEY": "<credential if selecting OpenAI models>",
        "ANTHROPIC_API_KEY": "<credential if selecting Anthropic models>",
        "GEMINI_API_KEY": "<credential if selecting Gemini models>",
        "GROQ_API_KEY": "<credential if selecting Groq models>",
        "DEEPSEEK_API_KEY": "<credential if selecting DeepSeek models>",
        "OLLAMA_HOST": "<address of the Ollama instance to consult>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
ceo_and_boardGather a panel's model responses, ask a designated model for a decision, and save the resulting files.
prompt_from_file_to_fileRead a local prompt by absolute path and write model answers to Markdown output files.
prompt_from_fileLoad prompt text from an absolute file path for the chosen models or default model set.
promptSubmit text directly to a chosen model set, falling back to configured models when omitted.
list_modelsDiscover model choices under one specified provider.
list_providersInspect the provider options exposed by the server.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Compare independently generated answers to one prompt without switching assistant integrations.
  • Reuse a prompt file and keep each model's output as a Markdown artifact.
  • Ask a designated decision model to weigh a panel's responses.
  • Discover provider-specific model choices before composing a multi-model request.

Strengths

  • Combines direct prompting, saved outputs, and a panel decision in one server.
  • Supports concurrent model consultation across the documented backends.
  • Missing keys disable individual providers instead of preventing the server from starting.
  • Includes provider discovery and model discovery rather than requiring every model name upfront.

Limitations

  • File-based operations require absolute prompt and output paths.
  • Each hosted backend needs its own usable credential.
  • Reasoning suffixes are tied to documented models and provider-specific limits.

Frequently asked questions

The configured default model list supplies the choices. Its first entry also participates in automatic correction of model names.

Parallel prompting gathers answers. The panel additionally asks a designated CEO model to decide from those answers and writes the results.

No. Startup reports providers with missing keys as unavailable while allowing use of the providers whose credentials are available.

License: Not stated in the README. Its structured license value is empty as well, so no license is assigned here.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

MiniMax MCP

AI Models & Agents

MiniMax MCP exposes MiniMax media APIs to compatible AI clients for speech, voice work, images, video, and music. It supports local stdio use and SSE deployment, with region-specific API credentials and configurable resource output.

pythonstdio1,590 GitHub stars

ElevenLabs MCP

AI Models & Agents

ElevenLabs MCP brings the vendor's speech and audio services into assistant workflows. This official integration supports voice work and transcription, with outputs delivered as files, MCP resources, or both.

pythonstdio1,535 GitHub stars

DeepSeek MCP Server

AI Models & Agents

DeepSeek MCP Server exposes DeepSeek V4 generation and account utilities to MCP clients. It offers chat, fill-in-the-middle completion, model discovery, balance checks, and in-process conversation management.

nodestdio353 GitHub stars

mcp-sequentialthinking-tools

AI Models & Agents

mcp-sequentialthinking-tools records stepwise reasoning with session history, branches, and revision metadata. It validates model-authored tool plans against a supplied tool list rather than discovering or choosing tools itself.

nodestdio587 GitHub stars