#124 · Primary category： AI Gateway & API Infrastructure
just-prompt
just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
Project last updated：08/10/25
GitHub Stars
739
Forks
132
Contributors
1
License
Other
Why we included this project
Wiring up a separate SDK for each LLM vendor is tedious, and just-prompt is built to skip that step. It's an MCP server that sends one prompt to models from OpenAI, Anthropic, Gemini, Groq, DeepSeek, or Ollama, so you can compare responses without maintaining per-provider code paths. The file-based tools fit batch work: point at a prompt file and get markdown responses written to disk. The ceo_and_board tool is the distinctive one, it sends your prompt to several 'board member' models and has a designated model make the final call, handy for quick multi-model consensus checks. Since it speaks the Model Control Protocol, it works with existing MCP clients and can run locally against Ollama as well as hosted APIs.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.