LightShip is answering right now. Last checked 7 min ago. Last commit 14 Sep 2026.
Governed access to production AI-agent traces in an existing ClickHouse store.
What the code does
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
finalDir := filepath.Join(s.exportDir, id)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
claude mcp add lightship --transport http https://lightship-production.up.railway.app/mcp{
"mcpServers": {
"lightship": {
"url": "https://lightship-production.up.railway.app/mcp"
}
}
}[mcp_servers.lightship]
url = "https://lightship-production.up.railway.app/mcp"{
"mcpServers": {
"lightship": {
"url": "https://lightship-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"lightship": {
"url": "https://lightship-production.up.railway.app/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://lightship-production.up.railway.app/mcp | streamable-http | needs auth | 236 ms | 7 min ago |
Alternatives to LightShip
same job, measured the same wayGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
AI agent observability for production traces, natural-language insights, and improvement loops.
Structured execution trace and span logging for AI agents
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
Every number in an AI answer traces back to the rows that produced it.
Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.
Debug production issues using Shipbook logs and Loglytics error insights.
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
LightShip — questions
Answers built from our own checks of this server.