Debugium is a multi-language debugger that allows users to debug various programming languages from a web interface, integrating AI-driven analysis through the Model Context Protocol (MCP).
From the registry: AI-driven live debugger with MCP bridge for Python, JS, TS, Rust, Java, C/C++

$ curl -fsSL https://raw.githubusercontent.com/Algiras/debugium/main/install.sh | bashhttps://github.com/Algiras/debugiumPlease install the `debugium` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install debugium binary** — Install via shell script on macOS/Linux, or build from source. Run: `curl -fsSL https://raw.githubusercontent.com/Algiras/debugium/main/install.sh | bash` (https://github.com/Algiras/debugium)
- **Run a debug session** — The MCP server connects to an active debug session; launch one with e.g. `debugium launch my_script.py --adapter python`.
Canonical MCP server config (stdio transport):
- command: `debugium`
- args: ["mcp"]
Note: 64 MCP tools covering DAP (Python, Node/TS, lldb for C/C++/Rust, Java, Scala, Wasm). MCP server attaches to session port from ~/.debugium/port.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.