
LightShip
io.github.lightshipHQ由 GitHub 账号 lightshipHQ 发布v0.1.0-alpha.1更新于 Oct 24, 2026
Governed access to production AI-agent traces in an existing ClickHouse store.
发布方自己的服务:ship.page
概览
LightShip 让助手在策略管控下访问存放在现有 ClickHouse 中的生产 AI 智能体追踪数据。
- 可以做什么
- 在 MCP 客户端中针对生产智能体的对话、工具调用与结果提出业务问题。
- 依据角色与属性策略(编译进 ClickHouse 查询)调查真实追踪,无需直接数据库凭据。
- 将大型调查的授权导出写入智能体工作区,仅在对话中返回路径与数量。
- 查看针对现有追踪表的排序键与索引建议(仅供参考)。
- 适用场景
- 适用于已将 OpenTelemetry 智能体追踪存入 ClickHouse 的团队,希望让业务专家或编码智能体在访问策略下查看真实对话与工具调用,而不必发放数据库凭据或把追踪复制到另一个可观测平台。
- 运行要求
- 远程 streamable HTTP 端点;认证使用在 LightShip 中创建的 bearer API 密钥,通过 Authorization 请求头发送。管理员需先将 LightShip 绑定到现有 ClickHouse OpenTelemetry span 表并定义角色与策略。
安装
在 SourceWeft 中
- 打开 控制台中的 LightShip,将其添加到工作区。
- 连接 Authorization token 凭据。它们会被私密存储,绝不会在公开页面上展示。
- 为需要使用其工具的对话启用该服务。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
交给智能体安装
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.lightshipHQ%2Flightship/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。其他 MCP 客户端
把它添加到你客户端的 mcpServers 配置中。
{
"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
- An administrator binds LightShip to an existing OpenTelemetry span table in ClickHouse.
- They choose which columns and map keys may be used for search and access rules.
- 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:
- Install the latest alpha
- Browse the Go package
- Connect your ClickHouse
- Define roles and policies
- Connect Codex, Claude, and other MCP clients
- Use the web UI
- Deploy and configure LightShip
- Browse the API reference
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.
来源:README.md,提交 0ff8db6
工具
0版本历史
1- v0.1.0-alpha.1最新Sep 16, 2026
评分
已满足适用检查项的 85%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通必需25 分
- 已声明认证方式必需10 分
- 已列出工具必需15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
其他 Ship 集成
ship.page
page.ship官方发布者
把 HTML 或多文件静态站点部署到可公开访问的网址,并在助手中管理、加密码保护、恢复或删除这些 drop。

StarShipIt MCP
由 GitHub 账号 devkindhq 发布
用于 StarShipIt 物流 API 的 MCP 服务器:订单、货件、面单、跟踪和费率AI 翻译
ShipSmarter Shipping
ca.mescolis
加拿大承运商聚合的寄件服务,让助手查询包裹物流、比较实时运费并查找寄件点,可选连接账户。

ShipLog
由 GitHub 账号 amacgregor 发布
ShipLog 的托管 MCP 服务器让助手读取 ShipLog 反馈板、添加与整理反馈,并起草或发布更新日志条目。

PubShip
由 GitHub 账号 pubship 发布
本地 MCP 服务器,让助手使用你自己的服务账号读取 Google Play 控制台信息,并在明确授权后准备变更。