{"id":"dive","name":"Dive","homepage":"https://github.com/OpenAgentPlatform/Dive","repo_url":"https://github.com/OpenAgentPlatform/Dive","category":"ai-ml","subcategories":["mcp-host","desktop-app","llm-client"],"tags":["mcp","desktop-app","electron","tauri","ollama","openai","anthropic","multi-llm","chat-interface","mcp-host"],"what_it_does":"An open-source desktop application that serves as an MCP host, connecting any LLM (ChatGPT, Anthropic, Ollama, OpenAI-compatible) with MCP servers through a unified chat interface. Supports stdio and SSE MCP transports, includes built-in tools (Fetch, File Manager, Bash), offers 24+ language support, and provides an installer agent for automatic MCP server configuration. Available in Electron and Tauri variants across Windows, macOS, and Linux.","use_cases":["Using local Ollama models with MCP tools via a desktop GUI","Connecting multiple LLM providers to MCP servers without coding","Having a unified chat interface that works with any MCP-compatible tool","Quick MCP server testing and experimentation through a visual interface","Non-technical users who want MCP tool access without CLI setup"],"not_for":["Headless or server-side MCP hosting (it is a desktop GUI app)","Production agent deployment pipelines","Users who prefer CLI-only workflows","Building custom MCP servers (it consumes them, not creates them)"],"best_when":"You want a visual desktop app to interact with MCP servers using various LLM providers, especially if you use local models via Ollama and want a polished chat UI.","avoid_when":"You need headless/programmatic MCP hosting, prefer CLI workflows, or already have a well-configured MCP client like Claude Code or Cursor.","alternatives":["Claude Desktop","Cursor","Cline","Roo Code","ChatMCP"],"af_score":49.0,"security_score":40.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"0.14.1","last_evaluated":"2026-03-01T09:50:05.494879+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}