Dive
by OpenAgentPlatform
Overview
A desktop AI conversational client that integrates with various AI models (LLMs) and custom/OAPhub tools (MCP servers) for enhanced functionalities, managing chat history and user preferences.
Installation
No command providedEnvironment Variables
- USER_DEFINED_MCP_TOOL_ENVIRONMENT_VARIABLE
Security Notes
The application allows users to define custom MCP (Model Context Protocol) servers with arbitrary commands, arguments, and environment variables. This feature, while intended for customization, presents a significant security risk as it enables arbitrary code execution on the user's host machine if a malicious or improperly configured MCP server definition is used. Additionally, the application has an option to 'Skip TLS Verification' for model providers, which, if enabled for untrusted endpoints, could expose user data to Man-in-the-Middle (MITM) attacks. User API keys and sensitive credentials are handled, and their secure storage/transmission by the backend (Rust/Python host) is crucial, though the frontend code does not fully detail these backend security measures.
Similar Servers
5ire
A desktop AI assistant client that integrates with various LLM providers and supports extensible tool and prompt functionalities via the Model Context Protocol (MCP).
osaurus
Osaurus is a native macOS LLM server running local language models with OpenAI and Ollama compatible APIs, enabling tool calling and a plugin ecosystem for AI agents.
wcgw
An MCP server that empowers AI chat applications to execute shell commands, edit code, and manage project context on a local machine for development tasks.
metorial-platform
The Metorial Platform is an open source integration platform for agentic AI, designed to connect any AI model to thousands of APIs, data sources, and tools with a single function call, built to scale for enterprise-grade AI applications.