Pagelive

Pagelive

Publish the pages you build with AI - as a private, tracked, secure link.

Category
访问服务器

README

Pagelive MCP connector

Publish the pages you build with AI — straight from the conversation — as private, branded, view‑tracked links.

Pagelive turns any HTML page (a proposal, deck, report, or demo) into a clean link you can actually send. Publish it from Claude, get a link that's private by default (noindex, optional password, served from an isolated content plane on Cloudflare), then see who opened it — opens, unique viewers, dwell time, by day, country, referrer — bot‑filtered, with an email the moment it's opened. Pages can carry a reply form whose submissions come back into the conversation. Update anytime; the link never changes.

This is the connector manifest + docs for Pagelive's hosted MCP server. The server is hosted by Pagelive (you don't run or install anything); this repo is the public home for the server.json, the tool reference, and example usage. Sign in with your Pagelive account — a free account works.

  • Website: https://pagelive.io/mcp
  • Docs / quickstart: https://pagelive.io/docs/quickstart-mcp
  • Connector URL (remote, OAuth): https://app.pagelive.io/api/mcp

Connect

The server is remote and uses OAuth 2.0 — there's nothing to install. Add the URL to any MCP‑capable client and sign in with your Pagelive account.

Claude (web / desktop) — Settings → Connectors → Add custom connector → paste https://app.pagelive.io/api/mcp → sign in when prompted.

Claude Code

claude mcp add --transport http pagelive https://app.pagelive.io/api/mcp

Any client that reads server.json — point it at this repo's server.json, or find Pagelive in the MCP Registry under io.pagelive/pagelive.

Tools (7)

Tool What it does
publish_page Publish an HTML page and get a live, shareable, view‑tracked URL. Pass an existing slug to replace a page instead of duplicating it.
update_page Edit a page you've published — targeted text edits or a full‑HTML replace. The link never changes.
list_pages List the pages you can access (personal + team) with their URLs, workspace, and view counts.
get_page_stats View analytics for a page — opens, unique viewers, dwell, top countries.
list_form_submissions Read the replies submitted through a page's reply form.
list_domains List your connected custom domains (Pro/Team).
list_workspaces List the workspaces you belong to (personal + teams).

Example prompts

  1. "Publish this page with Pagelive and give me the link."
  2. "Update my Q3 proposal page with this new version — keep the same link."
  3. "How many people opened my deck this week, and how long did they read?"
  4. "Did anyone reply to the proposal form? Show me the responses."
  5. "List my published pages and tell me which got views yesterday."

Live demos

  • https://pagelive.site/p/vantage-series-a-deck
  • https://pagelive.site/p/q2-performance-report
  • https://pagelive.site/p/q3-growth-proposal

Skill

This repo includes an optional Agent Skill that teaches the publish → share → track workflow, so an agent reaches for Pagelive at the right moment.

Auth & privacy

OAuth 2.0 sign‑in (free account works); no API key juggling. Published pages are noindex by default and can be password‑gated; analytics are bot‑filtered and contain no PII.

License

MIT — applies to the contents of this repo (manifest, docs, examples, skill). The hosted Pagelive service and its server source are separate and proprietary.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选