Data as of
Just Prompt for Cursor: Setup & Config
Cursor: Just Prompt lets an MCP assistant consult several language models and preserve their answers.
What you can do with Just Prompt in Cursor
Keep model comparison, saved answers, and a panel's final decision within one MCP workflow.
- Ask a designated decision model to weigh a panel's responses.
- Discover provider-specific model choices before composing a multi-model request.
Before you start: Just Prompt in Cursor
- Python and uv
- Local checkout with dependencies prepared using uv sync
- Credentials for chosen hosted providers, or an Ollama endpoint
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.
Just Prompt Cursor configuration
Choose Cursor configuration scope
For Just Prompt, open Project: .cursor/mcp.json User: ~/.cursor/mcp.json. Merge into mcpServers at project or user scope.
Add Just Prompt to Cursor
Use the just-prompt entry below in mcpServers. Keep Just Prompt's documented stdio connection fields and your other Cursor entries.
Check Just Prompt in Cursor
Just Prompt: Enable in Cursor’s MCP settings; inspect tools.
Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
{
"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>"
}
}
}
}Just Prompt tools available to Cursor
Just Prompt's stored tool list documents 6 tools; compare it with Cursor's connected tool list, because the stored list is not a live check.
- ceo_and_board
Find ceo_and_board under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
- prompt_from_file_to_file
Find prompt_from_file_to_file under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
- prompt_from_file
Find prompt_from_file under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
- prompt
Find prompt under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
Submit text directly to a chosen model set, falling back to configured models when omitted.
- list_models
Find list_models under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
Discover model choices under one specified provider.
- list_providers
Find list_providers under Just Prompt in Cursor's MCP settings; inspect its arguments when the agent requests a call.
Inspect the provider options exposed by the server.
Troubleshooting Just Prompt in Cursor
- Cursor must find uv for Just Prompt. Enable the project/user entry in MCP settings and inspect its tools.
- Review ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OLLAMA_HOST, OPENAI_API_KEY for Just Prompt before sharing project .cursor/mcp.json; project scope travels with the repository.
- Just Prompt uses stdio here: Cursor must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
- Known limitation: File-based operations require absolute prompt and output paths.
- Known limitation: Each hosted backend needs its own usable credential.
- Known limitation: Reasoning suffixes are tied to documented models and provider-specific limits.
- General Cursor troubleshooting lives in the /clients/cursor guide.
Just Prompt — details. Cursor guide