Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Search the source code (HTML, JavaScript, CSS) of hundreds of millions of websites.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://api.publicwww.com/mcp在终端中运行这条命令
claude mcp add --transport http publicwww https://api.publicwww.com/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"publicwww": {
"url": "https://api.publicwww.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"publicwww": {
"type": "http",
"url": "https://api.publicwww.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://api.publicwww.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 publicwww.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.2.0)于24天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Search the source code (HTML, JavaScript, CSS) of hundreds of millions of websites from an AI assistant: which sites load a script, use a library, carry a tracking id or a widget - then save them as a cluster and pull contacts, social profiles or tag ids out of their pages. PublicWWW runs a remote MCP server:
https://api.publicwww.com/mcp
Eleven tools: search (query, rows, page, snippets), account (plan, searches and extraction points left today), read_docs (PublicWWW's own documentation and price list in Markdown) and eight for clusters. The same documentation pages are MCP resources, publicwww://docs/ . Without signing in, the tool list and read_docs work; the other tools need a paid plan, and a free account gets plan_required from them - see limits.
Authorization: Bearer . Issue one on your profile page and keep it in the PUBLICWWW_TOKEN environment variable.| Client | How |
|---|---|
| Claude (web, desktop) | Customize → Connectors → Add custom connector, URL above - guide |
| ChatGPT | Plugins → Add → Add custom MCP server, OAuth - guide |
| Claude Code | the plugin below, or claude mcp add --transport http publicwww https://api.publicwww.com/mcp |
| Cursor | |
| VS Code | |
| Gemini CLI | gemini extensions install https://github.com/publicwww-com/publicwww-mcp |
| Codex CLI | codex mcp add publicwww --url https://api.publicwww.com/mcp --bearer-token-env-var PUBLICWWW_TOKEN |
| opencode | clients/opencode.json |
| Goose | clients/goose.config.yaml |
| DeepSeek Harness | dsh plugin --profile add github:publicwww-com/dsh-publicwww - plugin |
| Anything else | a config file from clients/ |
The Cursor button reads the token from PUBLICWWW_TOKEN; VS Code asks for it once and keeps it in its secret storage.
The MCP server (sign in with OAuth) and a skill that teaches the query syntax:
/plugin marketplace add publicwww-com/publicwww-mcp
/plugin install publicwww@publicwww
Then run /mcp, pick publicwww and choose Authenticate.
gemini extensions install https://github.com/publicwww-com/publicwww-mcp
It asks for the token once and keeps it in the system keychain.
skills/publicwww-search is a skill in the open Agent Skills format: how to write PublicWWW queries and use the tools. Copy the folder into your agent's skills directory (for example .agents/skills/ or ~/.claude/skills/).
| Query | Finds | |
|---|---|---|
"angular.min.js" | that exact text in the page source | |
bootstrap jquery | both, anywhere on the page | |
| `jquery (slick \ | swiper)` | jquery and either of the two |
"amcharts.js" -bootstrap | the first without the second | |
site:de bootstrap | only .de sites | |
depth:all "math.min.js" | inner pages too, not only home pages |
More: query syntax.
A cluster is a saved list of websites the assistant can build, combine and extract data from.
| Tool | What it does |
|---|---|
list_clusters | the account's clusters, newest first |
get_cluster | a page of the domains in a cluster |
create_cluster | from a search (query, costs one search) or a list of domains |
combine_clusters | and, or, or diff (in the first, not in the second) of clusters |
extract_from_cluster | values from the page source of every site: ready-made presets or your own regex, part after part |
rename_cluster | a new name |
delete_cluster | deletes for good; marked destructive, so the assistant asks you first |
Presets: email, phone, whatsapp, telegram, viber, line, facebook, instagram, x, linkedin, youtube, tiktok, pinterest, threads, bluesky, discord, github, google_play, app_store. Anything else is a regular expression in slashes whose first group is the value, e.g. /data-site-id="([0-9]+)"/i. Extraction spends the day's extraction points; an account keeps up to 100 clusters.
Ask in plain words: *"Find sites that load static.hotjar.com, save them as a cluster and get their contact emails and phones"* - the assistant runs create_cluster, then extract_from_cluster with the email and phone presets until the cluster is done. More: tools.
examples/mcp-curl.sh lists the tools, reads the account and runs a search with plain curl. Streamable HTTP, JSON answers, no sessions - see for developers.
For scripts the REST API is the simpler road - the same search, clusters and token, with CSV and NDJSON. Small clients: Python, JavaScript, PHP, Go, Ruby.
MIT