ship-page
One-call static page/site deploys for AI agents — POST HTML, a files map, or a zip and get back a live unguessable URL. Remote endpoint at https://ship.page/mcp, free tier needs no account or API key.
README
ship.page MCP server
Throw HTML at an API, get back a live URL. ship.page is a remote MCP server + plain REST API that lets an AI agent put content on the public internet — no account, no API key, no OAuth dance. One POST, one live *.shipped.page URL.
Endpoint
https://ship.page/mcp
Client config:
{
"mcpServers": {
"ship.page": { "url": "https://ship.page/mcp" }
}
}
Transport: Streamable HTTP. No auth required for anonymous deploys (7-day retention). Pass Authorization: Bearer sp_… (free key from the dashboard) for 30-day drops and higher limits; Pro drops never expire.
Tools
| Tool | What it does |
|---|---|
deploy_html |
Deploy a single HTML page, returns a live URL |
deploy_files |
Deploy a multi-file site from a path → content map (base64 for binaries) |
append_files |
Add files to an existing owned drop |
list_drops |
List the authenticated account's drops |
claim_drop |
Claim an anonymous drop into an account (slug + claim token) |
restore_drop |
Restore an expired drop (free ≤30d past expiry, paid ≤90d) |
delete_drop |
Delete an owned drop |
get_limits |
Plan matrix, quotas, and current usage |
get_account |
Account + plan status for the current key |
Errors come back as structured JSON with a human-readable hint agents can relay verbatim when something is plan-gated.
Local / stdio clients
For clients that only speak stdio, bridge via mcp-remote:
{
"mcpServers": {
"ship.page": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ship.page/mcp"]
}
}
}
The included Dockerfile packages exactly this bridge, so the server can be built and introspected as a standard container (e.g. by directory scanners).
REST API
Everything the MCP tools do is also plain HTTP. Full OpenAPI 3.1 spec: ship.page/openapi.json
curl -X POST https://ship.page/deploy \
-H "Content-Type: text/html" \
--data-binary @report.html
Links
- Docs: ship.page/docs/agents
- GitHub Action: bitgate/ship-page-action
- Glama connector: glama.ai/mcp/connectors/page.ship/ship-page
- Official MCP registry:
page.ship/ship-page
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。