原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

LinkedIn Toolkit

作者:OpenRecruiterTools版本 2.1.0i★ –i在你的电脑上运行
注册名称io.github.FormatixAI/linkedin-toolkit

安装

概览

作者提供的说明(英文原文)

LinkedIn for AI agents from your own Chrome session: search, profiles, lists, outreach queue.

PopNx MCP 的三大支柱

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。

它能帮你做什么

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。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 营销与社交媒体

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 0 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: LINKEDIN_TOOLKIT_HOME

你需要

  • npm已安装 Node.js(用于 npx 命令)

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 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "linkedin-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "linkedin-toolkit-mcp"
      ],
      "env": {
        "LINKEDIN_TOOLKIT_HOME": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add linkedin-toolkit --env LINKEDIN_TOOLKIT_HOME=your-value -- npx -y linkedin-toolkit-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "linkedin-toolkit": {
      "command": "npx",
      "args": [
        "-y",
        "linkedin-toolkit-mcp"
      ],
      "env": {
        "LINKEDIN_TOOLKIT_HOME": "your-value"
      }
    }
  }
}

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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "linkedin-toolkit": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "linkedin-toolkit-mcp"
      ],
      "env": {
        "LINKEDIN_TOOLKIT_HOME": "your-value"
      }
    }
  }
}

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。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • LINKEDIN_TOOLKIT_HOME env
    Directory for the local SQLite mirror and config. Defaults to ~/.linkedin-toolkit.

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。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

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

  • ! 注意

    作者与仓库一致

    发布者(FormatixAI)不是仓库所有者(OpenRecruiterTools);可能是其他人代为上架的

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“营销与社交媒体”中的其他服务器比较i

  • 星标数多于此分类中其他 2972 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2972 个服务器的 36% 更新
  • 基础检查结果等于或优于此分类中其他 2972 个服务器的 39%

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。

常见问题

LinkedIn Toolkit 安全吗?

它在 1 项适用的基础检查中通过了 0 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。

它需要哪些密钥或代码?

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。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(2.1.0)于2个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它?

同一分类中有:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

替代选择

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

MCP YouTube Transcript

作者:jkawamoto

An MCP server retrieving transcripts of YouTube videos

在你的电脑上运行★ 495MIT10天前更新
安装

Google Analytics MCP

作者:surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

在你的电脑上运行★ 244MIT9天前更新
安装

AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.

在云端运行★ 137MIT10天前更新
安装

作者的 README

打开 README

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。

LinkedIn Toolkit

LinkedIn blocks AI browser agents. This is how agents get in.

Operator, Browser Use, computer-use models and Playwright bots get challenged or banned on LinkedIn: headless fingerprints, datacenter IPs, machine-speed clicks. LinkedIn Toolkit gives any agent a safe, structured API to your own logged-in Chrome session — through the same internal endpoints the LinkedIn page itself calls, at human pace, under hard caps, with a human approval queue. It is also a free replacement for Waalaxy and PhantomBuster if you never touch an agent at all. No headless browser, no proxies, no cloud session, no telemetry, no subscription.

▶ Try it without installing · Install guide · Full-quality MP4

Recorded against the toolkit's own demo mode (lit serve --http --fake). Every tool call is real; everyone in it is invented.

Quick start

One command, then three clicks in Chrome.

npx linkedin-toolkit-mcp setup --client claude-code

That downloads the extension for your version, checks it, unpacks it to ~/.linkedin-toolkit/extension, prints the pairing token, waits for the extension to connect, and writes the MCP config block into your client's own config file — keeping every other server in it and backing the file up first. --client takes claude-desktop, claude-code, cursor, windsurf, vscode, n8n or print; add --dry-run to see what it would do without touching anything.

Then the three steps Chrome does not let any installer do for you:

  1. Open chrome://extensions — type it in the address bar; it does not come up in search.
  2. Turn on Developer mode, top right.
  3. Click Load unpacked and choose the folder setup printed.

Paste the pairing token into the popup → Settings → Local bridge, and check it took:

lit status

Rather do it by hand, or only want the extension and no agent?

Download linkedin-toolkit-extension-v*.zip from the Releases page, unzip it somewhere permanent (Chrome loads it from that folder on every start), then do the three steps above. Run npx linkedin-toolkit-mcp for the pairing token, and copy the config block for your client out of docs/clients.md.

docs/install.md is the same thing with screenshots, written for somebody who has never loaded an unpacked extension.

Mass unfollow — Preview first, then a small number, then the rest — is in docs/install.md. Read the "Connections are followed too" part before you decide the feature is broken: LinkedIn's Following list does not include your connections, who are followed automatically when you connect, so emptying that list to zero leaves a feed still full of posts. Ticking "Also unfollow my connections" scans your followers list instead, which is the only place that state is visible.

Every client's config file, path and shape: docs/clients.md · one page per ecosystem.

Not using MCP? lit serve --http gives you POST /actions/{action} and a generated GET /openapi.json. Examples in seven languages.

[!IMPORTANT]

Nothing sends without you. Copilot mode is the default: every write an agent makes queues

for your approval in the popup. Hard caps live in the extension — 100 invites, 150 messages, 500

profile visits, 1,000 search results a day — and no agent, CLI flag or config file can raise

them. Read the safety page before you turn Autopilot on.

What it does

ExtractProfiles (full page text + photo), search, Sales Navigator, Recruiter, post likers and commenters, group members, event attendees, company employees, your own connections and followers, message threads. CSV, JSON and SQLite out.
Lists and CRMNamed lists, tags, dedupe across lists, a "contacted before" flag on every profile, and intent signals: engaged with a post, changed job in the last 90 days, at a target company.
SequencesVisit, follow, connect with a note, message, InMail, like, comment, wait, and branch on accepted / replied / not accepted after N days. Variables with fallbacks, A/B variants per step, replies stop the sequence. 20 templates.
InboxUnified threads, unread, reply detection, sentiment tagging, saved replies, snooze.
Research PackA CSV of names or domains in; a dossier, an enriched CSV and a list out. Below.
Agent layer39 MCP tools, 4 resources, 3 prompts, a /actions HTTP API with OpenAPI 3.1, Node and Python clients, an n8n node, 6 skills.
SafetyJittered human delays, hourly and daily caps, business hours, 14-day warm-up, account presets, approval queue, 429 backoff, auto-pause on any security check (451 or a checkpoint redirect).
Local everythingchrome.storage.local, IndexedDB and a SQLite file on your machine. Read-only SQL over the lot. No server, no account, no telemetry.

Works with your agent

EcosystemHow
Claude Code, Claude Desktop, Cursor, Windsurf, Zed, Cline, OpenClaw, Codex CLI, Gemini CLInpx linkedin-toolkit-mcpMCP over stdio · config per client
Remote and hosted agents (Claude API MCP connector, ChatGPT connectors, Cloudflare Agents)lit serve --httpMCP over Streamable HTTP, token auth · risks
OpenAI Agents SDK, Vercel AI SDK, LangChain.js, Mastranpm i linkedin-toolkitTyped client + tool definitions · example
LangChain, LlamaIndex, CrewAI, AutoGen, Google ADK, Pydantic AI, smolagentspip install linkedin-toolkitPython client + @tool wrappers per framework · example
n8n, Make, Dify, Flowisen8n-nodes-linkedin-toolkit + MCP client nodeNodes for search, profile, invite, message, inbox, plus a webhook-fed trigger · workflow
Any HTTP agentlit serve --httpGET /openapi.json — OpenAPI 3.1 for custom GPTs, Dify and code generators
Agent Skills standardskills/Six skills that load unchanged in Claude Code, OpenClaw, and any compliant runtime

Structured errors carry code, message, retryAfter and howToFix, so an agent recovers or explains itself instead of retrying into a wall. There is an llms.txt and an agent quickstart written for an agent to read and self-install.

Browser agents vs LinkedIn Toolkit

Browser agentLinkedIn Toolkit
SessionHeadless or remote-controlled browser, cloud profileYour own Chrome, your own login
FingerprintSynthetic — patched, and detectable anywayYour real browser. Nothing to patch
IPDatacenter, or a residential proxy of dubious provenanceYour own connection
DetectionChallenged, degraded, then restrictedNo fingerprint or IP delta; volume and rhythm are still visible, which is why the caps exist
What the agent seesScreenshots, vision tokens, brittle selectorsTyped JSON per tool
Cost to source 100 profilesHundreds of screenshots3 tool calls
PaceMachine speedJittered human delays, business hours, warm-up
LimitsNone until LinkedIn imposes themHard caps no client can raise
On a challengeRetries, and makes it worseStops everything, tells the human
Human oversightWhatever you remember to buildApproval queue, on by default

The long version, with the actual detection mechanisms: Why browser agents fail on LinkedIn.

Why extensions broke, and why this one is built to be repaired

LinkedIn's web client now serves nearly all of its data through GET /voyager/api/graphql?queryId= .<32-hex hash>&variables=(...), and those hashes change with each web client release (current: 1.13.46474). The old REST Voyager paths that a generation of 2024–2025 extensions hard-coded return 400, 410 or 500 today. That is the mechanism — not a ban wave. This extension calls the same GraphQL queries the page calls, from inside your own tab, and keeps every query ID in one refreshable table with its capture date and client version: docs/voyager-endpoints.md. lit endpoints check reports which are ok, failed or unverified, and lit endpoints doctor names the query id whose hash went stale and the key in the table that holds it, so drift is a maintenance task rather than an architecture change.

Honestly: those IDs will drift, and re-capturing them is the contribution this project most needs. It is a table edit, not a rewrite — open DevTools on LinkedIn, filter the Network tab for voyager/api, and copy the queryId from a request the page makes; the same hashes are also literal strings inside LinkedIn's JS bundles if you would rather grep for them.

Versus the paid tools

Waalaxy ProPhantomBuster StarterSales-MindLinkedIn Toolkit
Price~€70/mo~$69/mo~$99/mo£0
SourceClosedClosedClosedMIT, all of it
Where the automation runsTheir cloud *(the extension imports only)*Their cloudTheir cloudYour own Chrome tab
Your sessionOn their serversOn their serversOn their serversNever leaves your machine
MCP server✗✗✗✓
Agent tools / SDKs✗✗✗✓ 39 tools, 9 frameworks
Local SQL over your data✗✗✗✓
Approval queue✗✗✗✓ on by default
Sequences with branching✓partial✓✓
Post engagers, groups, events✓✓partial✓
Inbox and sentiment✓✗✓✓
Team seats, dashboards✓✓✓✗ *(needs a server — see roadmap)*
Telemetry✓✓✓✗

Competitor prices are public list prices checked September 2026 and are approximate — they change, vary by currency and billing term, and each vendor's tiers differ. Feature claims are taken from each vendor's public product pages, also checked September 2026, and tiers move. Check their sites before deciding anything. Corrections welcome via PR — if we have a feature wrong, open one and it gets fixed.

Source for the Waalaxy column: its current Chrome extension listing, "Alien Copilot" by Waapi (Montpellier) — v1.1.3, updated August 2026, roughly 2,000 users, 3.0★ from 3 ratings — which describes itself as "your Waalaxy companion, helps you import prospects". On that listing the extension imports prospects into Waalaxy, and the automation runs on Waalaxy's servers using your session. Listing details read September 2026.

Research Pack

Drop in a CSV with any of name, linkedin_url, email, domain, company. Get back a dossier per row, an enriched CSV, and a list — all local.

lit 

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx