PageLens Analytics

io.pagelens由 pagelens.io 发布官方发布者v1.0.0更新于 Oct 27, 2026

Cookieless web analytics and AI Visibility: traffic, funnels, errors, and which AI bots read you.

已验证Streamable HTTP可网页运行网页搜索与抓取数据与分析

概览

AI 生成的概览

PageLens 网站分析远程 MCP 服务器：让助手读取流量、漏斗、错误、Web Vitals 与 AI 可见性数据，并可创建目标和标注。

可以做什么
  • 列出可访问的网站与已保存的细分，获取核心指标及同比时段对比和时间序列
  • 按页面、来源、渠道、UTM、国家、设备、浏览器、系统、语言、事件和外链做流量细分
  • 查看实时访客、近期会话、单次会话的浏览顺序、自定义事件、JavaScript 错误与 Core Web Vitals
  • 分析访问路径、转化漏斗、目标、同期群留存和已识别用户
  • 读取 Google Search Console 数据以及机器人和 AI 流量，包括 AI 爬虫抓取与 AI 引荐访问
  • 创建目标、在图表上添加日期标注，并为 GDPR 请求删除某用户数据
适用场景
适合让助手在不打开分析后台的情况下回答网站流量、转化、性能或 AI 可见性问题，或根据分析结果起草目标和标注。
运行要求
使用 app.pagelens.io 上的远程 streamable HTTP 端点，无需本地安装。需要 PageLens API 密钥，通过 Authorization 请求头以 Bearer 令牌发送。写操作（create_goal、add_annotation、delete_user_data）需要写密钥及成员或管理员权限。仅在已连接时才有 Google Search Console 数据。
安装前请注意
API 密钥是放在 Authorization 请求头中的机密，可访问其覆盖的网站。create_goal 和 add_annotation 会修改分析配置，delete_user_data 会永久删除某用户的事件、会话回放和资料。分析数据（含用户特征与会话详情）会发送给助手所用的模型提供方。

安装

在 SourceWeft 中

  1. 打开 控制台中的 PageLens Analytics，将其添加到工作区。
  2. 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。
  3. 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.pagelens%2Fpagelens/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。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "pagelens-analytics": {
      "type": "http",
      "url": "https://app.pagelens.io/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

工具

23

list_sites

List the websites this key can access, with visitors in the last 24 hours.

无需输入参数。

list_segments

Saved segments (named filter sets such as "Paid traffic" or "Mobile in Germany") that can be applied to any report with segment_id.

输入参数site_id必填

get_overview

Headline metrics (visitors, sessions, pageviews, pages per session, bounce rate, average session duration) for a period, compared with the previous period of the same length, plus a time series.

输入参数tofromperiodfilterssite_id必填timezonesegment_idinclude_series

get_breakdown

Top values of one dimension (pages, entry/exit pages, referrers, channels, UTM tags, countries, cities, browsers, OS, devices, languages, custom events, outbound links) with visitors and sessions.

输入参数tofromlimitperiodsearchfilterssite_id必填timezonedimension必填segment_id

get_pages

Per-page metrics: visitors, pageviews, entries, bounce rate and time on page.

输入参数tofromlimitperiodfilterssite_id必填timezonesegment_id

get_realtime

Visitors online right now (last 5 minutes) and what they are viewing.

输入参数site_id必填

list_sessions

Recent sessions with entry/exit page, pages viewed, duration, source, location and device.

输入参数tofromkindlimitperiodfilterssite_id必填user_idtimezonesegment_id

get_session

Every pageview and event in one session, in order.

输入参数site_id必填session_id必填

get_events

Custom events (sent with pagelens.track) and outbound clicks with counts and their properties.

输入参数tofromlimitperiodfilterssite_id必填timezonesegment_id

get_errors

JavaScript errors grouped by message, with occurrences, affected sessions and pages.

输入参数tofromlimitperiodfilterssite_id必填timezonesegment_id

get_web_vitals

Core Web Vitals from real visitors (LCP, INP, CLS, FCP, TTFB) at p50/p75/p90, overall and per page.

输入参数tofromperiodfilterssite_id必填timezonesegment_id

get_journeys

Most common page-to-page paths visitors take.

输入参数tofromlimitperiodfilterssite_id必填timezonesegment_id

run_funnel

Conversion funnel: how many sessions completed each step. Steps are pages (path, * wildcard allowed), custom event names, or a page scrolled at least `threshold` percent (type scroll). mode: ordered (default; other pages may come in between), strict (each step right after the previous one) or flexible (middle steps may be skipped). compare_previous adds the same funnel over the previous period.

输入参数tofrommodesteps必填periodfilterssite_id必填timezonesegment_idcompare_previous

list_goals

Goals with conversions and conversion rate for the period, compared with the previous period.

输入参数tofromperiodfilterssite_id必填timezonesegment_id

create_goal

Create a goal that counts sessions visiting a page, firing a custom event, or scrolling a page at least `threshold` percent (type scroll). Needs a write key and member access or higher.

输入参数nametype必填value必填site_id必填threshold

add_annotation

Mark a date on the charts (a release, a campaign, an outage). Needs a write key and member access or higher.

输入参数date必填text必填site_id必填

get_retention

Cohort retention of identified users (pagelens.identify): share of each daily or weekly cohort that came back in later periods.

输入参数unitsite_id必填timezone

list_users

Users active in the period: identified users (with traits) and anonymous visitors, with sessions, pageviews and first source.

输入参数tofromkindlimitperiodsearchfilterssite_id必填timezonesegment_id

get_user

Profile of one identified user (traits, first/last seen, totals) and their sessions.

输入参数site_id必填user_id必填

get_search_console

Google Search Console data for the site (when connected): clicks, impressions, CTR and average position in Google Search, by query, page, country or device, plus a daily series. Data lags about 2 days.

输入参数tofromlimitperiodsearchfilterssite_id必填timezonedimensionsegment_id

delete_user_data

GDPR erasure: permanently delete all events, session replays and the profile of one user on a site. Needs a write key and admin access.

输入参数site_id必填user_id必填

get_bots_and_ai

Bot and AI traffic: AI crawlers (GPTBot, ClaudeBot…), AI assistants fetching pages, search engines, and human visits referred by AI assistants (ChatGPT, Perplexity, Claude…).

输入参数tofromperiodfilterssite_id必填timezonesegment_id

get_ai_visibility

How the site shows up in AI assistants, per AI company (OpenAI/ChatGPT, Anthropic/Claude, Perplexity, Google/Gemini…) and per page: crawler reads, live fetches while answering a person, human visits sent back, purchases and revenue, robots.txt access, and plain-language findings.

输入参数tofromperiodfilterssite_id必填timezonesegment_id

版本历史

1
  1. v1.0.0最新Oct 12, 2026

评分

已满足适用检查项的 83%

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
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。