Ingero

Name: Ingero
Author: ingero-io

by ingero-iocommunityv0.8.2

Ingero is a production-grade eBPF agent that traces GPU workloads, providing causal analysis of performance issues with minimal overhead and no code changes required.

From the registry: eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging

GitHub Repository Website

Install & configure

Prerequisites

required
Install ingero
Download the pre-built binary from GitHub Releases (or build from source with make)
https://github.com/ingero-io/ingero/releases
required
Trace database
Capture a trace database first (e.g., 'sudo ingero trace'), then point the MCP at the resulting trace.db file

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `ingero` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install ingero** — Download the pre-built binary from GitHub Releases (or build from source with make) (https://github.com/ingero-io/ingero/releases)
- **Trace database** — Capture a trace database first (e.g., 'sudo ingero trace'), then point the MCP at the resulting trace.db file

Canonical MCP server config (stdio transport):
- command: `ingero`
- args: ["mcp","--db","trace.db"]

Note: Ingero is a Go CLI for eBPF-based GPU tracing/analysis. The 'mcp' subcommand serves its query engine as an MCP. Also supports --http Streamable HTTP mode with TLS 1.3.

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.

Note: Ingero is a Go CLI for eBPF-based GPU tracing/analysis. The 'mcp' subcommand serves its query engine as an MCP. Also supports --http Streamable HTTP mode with TLS 1.3.