# Superlog

Hooks your coding agent up to application telemetry, so it can pull logs, traces, metrics and incidents on its own while you debug production.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1470
- Author: superloglabs
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/superloglabs/superlog
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/superlog

## What it does

Superlog is an open-source telemetry system built around OpenTelemetry. It takes in traces, logs and metrics, folds scattered signals into incidents, and gives you a workspace for chasing down problems in production. The MCP server exposes the same data to an agent: instead of pasting console output into chat, you ask for the logs or traces you need.

The community edition in the repo ships a web app and API, an OTLP intake proxy, workers that group incidents and run background jobs, a Postgres schema, and telemetry queries backed by ClickHouse. Investigation runtimes are pluggable, and a default `community` runner writes a local incident summary. Running it locally takes Node.js 20+, pnpm 9+ and Docker — bring the stack up with `docker compose up -d`, run migrations, then `pnpm dev`. The services listen on `http://localhost:5173`, `http://localhost:4100` and `http://localhost:4101`.

The hosted endpoint sits at `https://api.superlog.sh/mcp`, so pointing an agent at it needs no local stack and no API key. Apache-2.0 means you can read and modify the code.

## Requirements
- Remote server: `https://api.superlog.sh/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http superlog https://api.superlog.sh/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add superlog --url https://api.superlog.sh/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "superlog": {
            "url": "https://api.superlog.sh/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "superlog": {
            "type": "http",
            "url": "https://api.superlog.sh/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http superlog https://api.superlog.sh/mcp
```

## When to use it
- trace a production failure back to its cause
- turn scattered alerts into one incident
- run an OpenTelemetry stack locally for debugging
- give an agent access to production metrics
- review what broke overnight

## Example prompts
- List the latest Superlog incidents and dig into the most recent one
- Find requests in the traces that took over a second in the last hour
- Pull metrics for the `api` service and show me where p95 dropped

## Similar
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [Oh My Posh Validator](https://affpapa.org/en/nevibecode/mcp/oh-my-posh-validator.md) — MCP server · ★ 23643
- [Keploy](https://affpapa.org/en/nevibecode/mcp/keploy.md) — MCP server · ★ 18727
- [Coder](https://affpapa.org/en/nevibecode/mcp/coder.md) — MCP server · ★ 17160
- [mcp](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — MCP server · ★ 12109

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md