# Superlog — MCP server card for AI agents

Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.

Registry name: `sh.superlog/superlog` · category: Cloud and DevOps · version 1.0.0 · updated 2026-07-21

## Connect
- Remote (Claude Code): `claude mcp add --transport http superlog https://api.superlog.sh/mcp`

## Facts
- Repository: https://github.com/superloglabs/superlog (1,487 stars)
- Website: https://superlog.sh

Before you connect a server: read its repository, and give it only the permissions and keys it needs.

## Links
- AgentGid page: https://agentgid.com/mcp/servers/sh-superlog-superlog/


## Superlog: ask your coding assistant why production broke

Superlog collects the logs, traces and metrics your app sends while it runs and groups errors into incidents. Its MCP server lets a coding assistant such as Claude Code, Codex or Cursor search that data and explain an incident. With write access it can also add alerts and dashboards for you.

### Where to use it
- Find the cause of an error: Ask your assistant what failed in the last hour. It searches the logs and request traces of your app instead of you pasting logs into the chat.
- Explain an incident from its link: Paste the link of an incident from Superlog and the assistant reads it, with what the investigation agent found.
- Turn a fix into an alert: After a bug is fixed, the assistant adds an alert so the same failure warns you next time. It can try the alert on current data before saving it.
- Quiet noisy errors: When the same harmless error keeps opening incidents, the assistant changes the filter that decides what counts as an issue. It shows the effect on the last day first.
- A dashboard for one service: Ask for a dashboard of errors and slow requests for one part of your app. The assistant creates it and adds charts and tables.
- Teach the investigator about your system: Write down how your system is built and what you learned from past bugs. Superlog's own investigation agent reads it on every later run.

### How to start
- Send your app's logs and traces to Superlog (hosted, or your own copy run with Docker), so there is data to ask about.
- Add the server to your coding assistant and sign in in the browser.

```
claude mcp add --transport http superlog https://api.superlog.sh/mcp
```

- For a tool without browser sign-in, create a personal access token in Settings, Project, MCP tokens and send it as an Authorization Bearer header.

### License
The community edition is open source under the Apache-2.0 license and free to run yourself, also in paid products. The hosted Superlog Cloud has a free tier and paid plans.

### Good to know
- Superlog only knows what your app sends it. Set up sending logs and traces first, or the assistant finds nothing.
- A connection with write access can create, change and delete alerts, dashboards and the shared home page. A read-only connection gets only the reading tools.
- The server tells connected assistants to save what they learn as memories for Superlog's own investigation agent, so expect it to write notes into your project.
- Switching the active project lasts for as long as the sign-in token, not only for one chat.
- Hosted plans include 5 million logs a month kept for 30 days; more logs cost extra on Pro and Team.

Checked 2026-11-10 against: https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/README.md, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/LICENSE.md, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/server.json, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/server.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/alerts.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/dashboards.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/incidents.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/agent-config.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/analytics.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/mcp/scope-authorization.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/api/src/alerts-service.ts, https://github.com/superloglabs/superlog/blob/78123eebd23d41c54bd09c70a563ba311d7546e6/apps/web/src/onboarding/McpInstallDialog.tsx, https://github.com/superloglabs/superlog/releases.atom, https://superlog.sh/, https://superlog.sh/privacy, https://superlog.sh/llms.txt

### Mistakes to avoid
- Don't: create_alert with aggregation 'avg' on logs, or a metric alert without metric_name → Do: count for logs and traces; sum or avg plus metric_name for source metric (The tool rejects other combinations.)
- Don't: update_issue_filter straight away → Do: get_issue_filter, then preview_issue_filter, then update_issue_filter (Each bucket you send replaces the old one, and the server's own guidance says to preview first.)
- Don't: set_project_context with only the new sentence → Do: read get_project_context, edit the returned text, send the whole text back (8000 characters at most) (The tool replaces the whole field, so a partial text erases the rest.)
- Don't: filtering failed requests by the span's status (OK or ERROR) to find HTTP 500s → Do: span_attrs [{key:"http.response.status_code", value:"500"}] on query_traces (HTTP status, route and method sit in span attributes, not in the span status.)
- Don't: delete_agent_memory to retire an outdated note → Do: update_agent_memory with status 'archived' (Delete is permanent; archiving can be undone.)

### Questions
- Does my assistant need a key? No for Claude Code, Codex and Cursor, which sign in through the browser. A personal access token is the option for tools without that sign-in.
- Can I run it on my own servers? Yes. The community edition runs locally with Docker, Node.js 20+ and pnpm 9+, with its API on port 4100.
- Do I have to drop Sentry or Datadog? No. Superlog connects to the tools you already use and adds their context.
- Is my data used to train AI models? The privacy policy says Superlog does not use customer content to train foundation models, and its subprocessors may not either.

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
