MCP Server

Active

Apache-2.0

Superlog MCP Server

sh.superlog/superlog

Open-source observability agent that ingests traces, logs, and metrics to debug production systems.

What is the Superlog MCP server?

Superlog is an open-source agentic telemetry system that ingests traces, logs, and metrics from your applications. It groups noisy signals into incidents and provides a local-first workspace for investigating and fixing production issues.

Superlog is an OpenTelemetry-based observability platform that collects and correlates traces, logs, and metrics to surface actionable incidents. Use it to query your telemetry data, understand system behavior, and debug production problems with AI-assisted investigation.

How to install Superlog

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "superlog": {
      "url": "https://api.superlog.sh/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Query logs — Search and analyze application logs
Query traces — Inspect distributed traces across your system
Query metrics — Access performance and system metrics
Incident grouping — Automatically group related signals into incidents
Agent investigation — Run agentic investigation workflows on telemetry data

Use cases

Debug production incidents by correlating logs, traces, and metrics
Automatically group noisy alerts into coherent incidents for faster triage
Query historical telemetry to understand system behavior and root causes
Use AI agents to investigate and suggest fixes for infrastructure issues
Monitor application health and performance with OpenTelemetry data

Superlog MCP server FAQ

What is Superlog?

Superlog is an open-source observability workspace for OpenTelemetry data. It ingests traces, logs, and metrics, groups signals into incidents, and provides tools to debug production systems.

Is Superlog free?

Yes, Superlog has a fully open-source community edition that is free. They also offer a hosted Superlog Cloud with a free tier and pay-as-you-go plans.

What data sources does it support?

Superlog ingests OpenTelemetry (OTLP) data including traces, logs, and metrics. It uses an OTLP intake proxy to receive telemetry.

How do I install Superlog?

You can install the community edition locally with Docker and pnpm (Node.js 20+). Run `docker compose up -d` and `pnpm dev` to start the stack. The web app runs on localhost:5173.

Can I use this with Claude or Cursor?

Yes, this is an MCP server available at https://api.superlog.sh/mcp. You can connect it to Claude or Cursor to query logs, traces, metrics, and incidents.

What are incidents?

Incidents are automatically grouped collections of related signals (logs, traces, metrics) that indicate a problem. Superlog's worker processes group noisy signals to surface actionable issues.

README (reference)

Source of truth, from the repository.

</div> <p align="center"> <a href="https://superlog.sh">Website</a> · <a href="https://github.com/superloglabs/superlog">Code</a> · <a href="https://github.com/superloglabs/skills">Skills</a> · <a href="https://github.com/superloglabs/otel-helpers">Helpers</a> · <a href="https://discord.gg/wJ56aRh8hx">Discord</a> </p>

About

Superlog is an open-source agentic telemetry system. It ingests traces, logs, and metrics, groups noisy signals into incidents, and watches your infra while you sleep.

Installation

You can install Superlog in your project by using our skills in your favourite coding agent:

Run npx skills add superloglabs/skills --all and use the skills to install Superlog in this project

What is Superlog?

Superlog is an open-core observability workspace for OpenTelemetry data. It ingests traces, logs, and metrics, groups noisy signals into incidents, and gives teams a local-first product surface for debugging production systems.

This repository contains the fully open-source, free community edition:

Web app and API
OTLP ingest proxy
Worker processes for incident grouping and background jobs
Postgres schema and ClickHouse-backed telemetry queries
Agent runner interfaces for pluggable investigation runtimes
A default community agent runner that records a local incident summary

We also provide a hosted Superlog Cloud edition with a free tier, a pay-to-go plan and monthly credit packs.

Quick Start

Prerequisites:

Node.js 20+
pnpm 9+
Docker

Install dependencies:

pnpm install

Start the local stack:

docker compose up -d
pnpm --filter @superlog/db db:migrate
pnpm dev

The default local services are:

Web: http://localhost:5173
API: http://localhost:4100
OTLP intake: http://localhost:4101

Development

Run typechecks:

pnpm typecheck

Repository Layout

apps/web - Vite/React frontend
apps/api - HTTP API
apps/proxy - OTLP intake proxy
apps/worker - background workers and agent orchestration
packages/db - Drizzle schema and migrations
packages/fingerprint - telemetry fingerprinting helpers

License

Superlog is licensed under the Apache License 2.0.

Related MCP servers

Swarm0x

Active

Run before you buy on Robinhood Chain: a simulated buy and sell, plus trades your own wallet signs.

Python

MIT

View repository →

tashan

Active

Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.

HTML

View repository →

sh.tibia/tibiawiki-mcp

Active

TibiaWiki knowledge base: attribute queries over creatures, items, NPCs, quests and spells

TypeScript

View repository →

twitr.sh

Active

X/Twitter reads, search, monitoring, and posting via AI agents—pay-per-call in USDC, no API keys or signup.

MIT

View repository →

uldl

Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.

uploads.sh

Active

Host file artifacts from coding agents and attach them to GitHub PRs with stable public URLs.

TypeScript

Apache-2.0

View repository →