Ingero
eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
ghcr.io/ingero-io/ingero:v0.8.2claude mcp add ingero -- docker run -i --rm ghcr.io/ingero-io/ingero:v0.8.2
{
"mcpServers": {
"ingero": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ingero-io/ingero:v0.8.2"
]
}
}
}
Frequently asked questions
What is Ingero?
eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging
How do I install Ingero?
It runs on your machine. In Claude Code: claude mcp add ingero -- docker run -i --rm ghcr.io/ingero-io/ingero:v0.8.2. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Ingero need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Ingero open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Ingero?
It is published by ingero-io. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.