Governed access to production AI-agent traces in an existing ClickHouse store.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
One-click editor setup isnโt available for this listing yet โ we donโt have a confirmed install command, and weโd rather show nothing than point your editor at the wrong package or host. Follow the projectโs own setup instructions, linked above.
Faster production-agent iteration, without a developer bottleneck.
LightShip gives domain experts governed, self-serve access to production agent traces. It sits in front of your existing OpenTelemetry data in ClickHouse, so humans and AI coding agents can investigate real conversations and tool calls without database credentials or another observability silo.
Documentation ยท Website ยท Try the hosted demo ยท Contribute
Open the hosted demo. Its sign-in page provides the credentials for a disposable administrator account. The dataset contains 132 recorded synthetic support-agent conversations across two fictional retailers.
In the web UI you can:
Follow the tenant-scoped access guide to explore the access-control setup and verify its boundary. To investigate the traces conversationally, follow the MCP connection guide, then use the tested prompt sequence in the tenant-scoped access guide.
The deployment is an intentionally editable sandbox. Do not enter real or sensitive data.
A trace is the authorization unit: one matching span grants access to the complete trace. LightShip never gives restricted users direct ClickHouse credentials.
Query performance depends on the layout and indexes of your existing ClickHouse trace table. After you select the fields available to filters and access policies, LightShip reviews the table's sorting key and skip indexes and suggests DDL for missing indexes. These recommendations are advisory: LightShip never changes your ClickHouse schema automatically. See how to review the optimization report.
The documentation contains the maintained setup and reference material:
Need help deploying LightShip in your environment? Talk to us.
LightShip protects only requests sent through LightShip. Direct ClickHouse access bypasses its policies. It does not currently detect PII, redact payloads, or hide individual spans. Query auditing is best-effort, so an audit-write failure is logged without failing the trace request.
LightShip is an experimental alpha with no stable release. Evaluate it using synthetic or non-sensitive data in an isolated environment. Read the security guidance and current limitations before deployment.
We want to help make autonomous work trustworthy and governable. If your team operates AI agents in production, we would love to hear what LightShip should support next.
Talk to us or open a GitHub issue.
See CONTRIBUTING.md for development and testing, SECURITY.md for vulnerability reporting, and CHANGELOG.md for changes. LightShip is licensed under Apache-2.0.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/lightship)<a href="https://allmcps.com/mcp/lightship"><img src="https://allmcps.com/api/badge/lightship?style=directory" alt="LightShip on AllMCPs" /></a>