Allows an AI client to observe and fix applications by querying logs, traces, metrics, and incidents from OpenTelemetry data.
Also known as superloglabs/superlog
- Stars
- 1,483
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 14, 2026
- License
- Apache-2.0
What is Superlog MCP?
Superlog allows an AI client to observe and fix applications by querying logs, traces, metrics, and incidents from OpenTelemetry data.
Summary generated from the project's README
About Superlog MCP server
Observing and repairing applications by querying telemetry data is what Superlog enables for developers using AI clients. It functions as an agentic telemetry system that ingests traces, logs, and metrics to group noisy signals into actionable incidents. This allows an AI agent to monitor infrastructure and debug production systems through a local-first interface.
Users can integrate these capabilities into their favorite coding agents by running the command npx skills add superloglabs/skills --all. The system is built on OpenTelemetry data and utilizes a stack including a web app, an OTLP ingest proxy, and worker processes for background jobs. While a hosted Cloud edition exists with various pricing plans, the community edition provides a fully open-source workspace featuring a Postgres schema and ClickHouse-backed telemetry queries.
What you can do with it
- 1Debug production system errorsAsk your AI client to investigate specific application failures using ingested telemetry data.
- 2Group noisy telemetry signalsHave an agent organize scattered logs and metrics into distinct, manageable incidents.
- 3Automate infrastructure monitoringSet up an agent to watch your infrastructure and report on issues automatically.
Written from the project's README. Every use case is checked against a quote from it.
How to install Superlog MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Superlog MCP in Claude Code
$ claude mcp add --transport http superlog https://api.superlog.sh/mcpInstall Superlog MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"superlog": {
"url": "https://api.superlog.sh/mcp"
}
}
}Install Superlog MCP in VS Code
.vscode/mcp.json
{
"servers": {
"superlog": {
"type": "http",
"url": "https://api.superlog.sh/mcp"
}
}
}Install Superlog MCP in VS Code CLI
$ code --add-mcp '{"name":"superlog","type":"http","url":"https://api.superlog.sh/mcp"}'Install Superlog MCP in Codex
$ codex mcp add superlog --url https://api.superlog.sh/mcpInstall Superlog MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.superlog] url = "https://api.superlog.sh/mcp"
Install Superlog MCP in Gemini CLI
$ gemini mcp add -s user --transport http superlog https://api.superlog.sh/mcpInstall Superlog MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"superlog": {
"url": "https://api.superlog.sh/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHub
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
communityagent 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 frontendapps/api- HTTP APIapps/proxy- OTLP intake proxyapps/worker- background workers and agent orchestrationpackages/db- Drizzle schema and migrationspackages/fingerprint- telemetry fingerprinting helpers
License
Superlog is licensed under the Apache License 2.0.
Superlog MCP questions
How do I add Superlog MCP to Claude Code?
Run claude mcp add --transport http superlog https://api.superlog.sh/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Superlog MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What is Superlog?
Superlog is an open-core observability workspace for OpenTelemetry data that ingests traces, logs, and metrics to group signals into incidents.
How do I install Superlog in my project?
You can install it by using skills in your coding agent with the command: npx skills add superloglabs/skills --all.
What are the local service ports for Superlog?
The local services run on Web at port 5173, API at port 4100, and OTLP intake at port 4101.