LightShip

io.github.lightshipHQPublished by GitHub account lightshipHQv0.1.0-alpha.1Updated Oct 24, 2026

Governed access to production AI-agent traces in an existing ClickHouse store.

The publisher's own server: ship.page

VerifiedStreamable HTTPWeb executableDatabasesSecurity & MonitoringData & Analytics

Overview

AI-generated overview

LightShip gives assistants governed, policy-scoped access to production AI-agent traces stored in an existing ClickHouse OpenTelemetry table.

What you can do
  • Ask business questions across production agent conversations, tool calls and outcomes from an MCP client.
  • Investigate real traces through role- and attribute-based policies compiled into ClickHouse queries, without direct database credentials.
  • Write authorized exports of large investigations into the agent workspace, returning only paths and counts to the conversation.
  • Review advisory index and sorting-key suggestions for the existing trace table.
When to use it
Useful when a team already stores OpenTelemetry agent traces in ClickHouse and wants domain experts or coding agents to explore real conversations and tool calls under access policies, instead of handing out database credentials or copying traces into another observability platform.
Requirements
A remote streamable HTTP endpoint; authentication is a bearer API key created in LightShip, sent in the Authorization header. An administrator must first bind LightShip to an existing ClickHouse OpenTelemetry span table and define roles and policies.
Before you install
Experimental alpha with no stable release; evaluate with synthetic or non-sensitive data in an isolated environment. It does not detect PII, redact payloads or hide individual spans, and one matching span grants access to the complete trace. Policies only cover requests sent through LightShip, since direct ClickHouse access bypasses them, and query auditing is best-effort. The bearer API key is a secret.

Installation

In SourceWeft

  1. Open LightShip in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lightshipHQ%2Flightship/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "lightship": {
      "type": "http",
      "url": "https://lightship-production.up.railway.app/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

LightShip

Faster production-agent iteration, without a developer bottleneck.

[CI] [Release] [Container] [License]

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 · Website · Contribute

Why LightShip

  • Find the patterns behind failures. Ask business questions across conversations, tool calls, and outcomes using Codex, Claude, or another MCP client.
  • Keep your existing trace store. Bind LightShip to your OpenTelemetry table without copying traces into a separate platform.
  • Instrument once; define policies later. Select existing columns and attribute keys as authorization inputs, then create or change policies without re-instrumenting. The same policy governs the web UI, REST API, and MCP.
  • Keep large investigations out of model context. The local MCP companion writes authorized exports into the agent workspace and returns only paths and counts to the conversation.

How it works

  1. An administrator binds LightShip to an existing OpenTelemetry span table in ClickHouse.
  2. They choose which columns and map keys may be used for search and access rules.
  3. LightShip compiles each caller’s roles and attributes into the ClickHouse query before returning any trace through the web UI, REST, or MCP.

A trace is the authorization unit: one matching span grants access to the complete trace. LightShip never gives restricted users direct ClickHouse credentials.

Performance

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.

Get started

The documentation contains the maintained setup and reference material:

Need help deploying LightShip in your environment? Talk to us.

Security and project status

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.

Feedback

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.

Contributing

See CONTRIBUTING.md for development and testing, SECURITY.md for vulnerability reporting, and CHANGELOG.md for changes. LightShip is licensed under Apache-2.0.

Source: README.md at commit 0ff8db6

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v0.1.0-alpha.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Ship integrations

ship.page

page.shipOfficial publisher

Deploy HTML or multi-file static sites to live public URLs, and manage, password-protect, restore or delete those drops from an assistant.

Streamable HTTPWeb executable
Cloud & Infrastructure11 toolsOct 25, 2026

StarShipIt MCP

Published by GitHub account devkindhq

MCP server for the StarShipIt shipping API: orders, shipments, labels, tracking and rates

STDIODesktop only
Not validated yetNov 3, 2026

ShipSmarter Shipping

ca.mescolis

Canadian multi-carrier shipping service that lets an assistant track parcels, compare live carrier rates and find drop-off points, with optional account access.

Streamable HTTPWeb executable
Location & Lifestyle8 toolsOct 31, 2026

ShipLog

Published by GitHub account amacgregor

ShipLog's hosted MCP server lets an assistant read a ShipLog feedback board, add and triage feedback, and draft or publish changelog entries.

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredOct 30, 2026

PubShip

Published by GitHub account pubship

Local MCP server that lets an assistant read and, when explicitly enabled, prepare Google Play Console changes using your own service account.

STDIODesktop only
Developer ToolsNot validated yetOct 24, 2026