MCP.so
Sign In

Dive AI Agent 🤿 🤖

@openagentplatform

About Dive AI Agent 🤿 🤖

Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨

Overview

What is Dive AI Agent 🤿 🤖?

Dive AI Agent is an open-source MCP Host Desktop Application that seamlessly integrates with any large language model (LLM) supporting function calling capabilities. It runs on Windows, macOS, and Linux.

How to use Dive AI Agent 🤿 🤖?

Download the latest release from GitHub – .exe for Windows (pre-installed Python and Node.js), .dmg for macOS, or .AppImage for Linux (macOS/Linux require manual Python and Node.js setup). After installation, configure LLM API keys and MCP servers via the UI or by editing the JSON configuration in Dive’s MCP settings.

Key features of Dive AI Agent 🤿 🤖

  • 🌐 Universal LLM support: ChatGPT, Anthropic, Ollama, Gemini, Mistral, and OpenAI-compatible models
  • 💻 Cross-platform desktop app for Windows, macOS, and Linux
  • 🔄 Model Context Protocol (MCP) integration via stdio and SSE
  • 🌍 Multi-language UI: Traditional Chinese, Simplified Chinese, English, Spanish, Japanese
  • ⚙️ Advanced API key and model management with custom instructions
  • 🔧 UI-based add/edit/delete of MCP tools and server configurations

Use cases of Dive AI Agent 🤿 🤖

  • Connect any function-calling LLM to powerful MCP tools (e.g., fetch web pages, download YouTube content, access filesystem)
  • Manage multiple LLM providers and API keys from a single desktop interface
  • Build custom AI agents with personalized system prompts and tool sets
  • Use MCP servers locally (stdio) or remotely (SSE) for flexible agent workflows

FAQ from Dive AI Agent 🤿 🤖

What is Dive AI Agent?

It is an open-source desktop application that acts as an MCP host, letting any function-calling LLM interact with MCP tools.

Which LLMs are supported?

Dive supports ChatGPT, Anthropic, Google Gemini, Mistral AI, Ollama, and any OpenAI-compatible model.

How do I install and set it up?

Download the appropriate installer for your OS (Windows .exe, macOS .dmg, Linux .AppImage). On Windows the environment is pre‑packaged; on macOS/Linux you must install Python and Node.js manually. Then add your LLM API keys and optionally configure MCP servers via the UI or JSON.

Can I add my own MCP servers?

Yes. You can add MCP servers by editing the JSON configuration in Dive’s settings. Both stdio and SSE transports are supported.

Is Dive AI Agent free and open-source?

Yes, it is open‑source and available on GitHub. There is no mention of paid licensing or pricing.

Comments

More Desktop Chat MCP clients