Diagnose GPU and ML training failures (CUDA OOM, NCCL timeouts, Xid faults) locally or via cloud.
Power your agent
The publisher's own command. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
npx -y [email protected]Claude Code has no install link for a local command. Copy the command below and run it in a terminal.
DENPEX_API_KEY=<secret> DENPEX_OFFLINE_ONLY=<value> claude mcp add io.github.denpex-denpex-mcp -- npx -y denpex-mcp@0.2.45Run in a terminal.
{ "mcpServers": { "io.github.denpex-denpex-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ], "env": { "DENPEX_API_KEY": "<secret>", "DENPEX_OFFLINE_ONLY": "<value>" } } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
README is not crawled yet. Open the repository
Diagnose GPU and ML training failures (CUDA OOM, NCCL timeouts, Xid faults) locally or via cloud.
{ "mcpServers": { "io.github.denpex-denpex-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ], "env": { "DENPEX_API_KEY": "<secret>", "DENPEX_OFFLINE_ONLY": "<value>" } } }}Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
The publisher lists these environment variables: DENPEX_API_KEY, DENPEX_OFFLINE_ONLY.
Denpex runs locally over stdio.
Last checked 2026-11-18. Diagnose GPU and ML training failures (CUDA OOM, NCCL timeouts, Xid faults) locally or via cloud.