概览
作者提供的说明(英文原文)
Read LinkedIn profiles, companies, jobs and messages via your own browser session
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。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查;尚未扫描代码
- 使用情况i非常新↓ 27/周 · ★ –
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
- 你需要填写:LINKEDIN_COOKIE
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 1 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_COOKIE,LINKEDIN_HEADLESS,LINKEDIN_MIN_INTERVAL,LINKEDIN_MAX_PER_HOUR
标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
- PyPI已安装 Python 的 uv(用于 uvx 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-api": {
"command": "uvx",
"args": [
"linkedin-api-mcp"
],
"env": {
"LINKEDIN_COOKIE": "your-value",
"LINKEDIN_HEADLESS": "your-value",
"LINKEDIN_MIN_INTERVAL": "your-value",
"LINKEDIN_MAX_PER_HOUR": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add linkedin-api --env LINKEDIN_COOKIE=your-value --env LINKEDIN_HEADLESS=your-value --env LINKEDIN_MIN_INTERVAL=your-value --env LINKEDIN_MAX_PER_HOUR=your-value -- uvx linkedin-api-mcp运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"linkedin-api": {
"command": "uvx",
"args": [
"linkedin-api-mcp"
],
"env": {
"LINKEDIN_COOKIE": "your-value",
"LINKEDIN_HEADLESS": "your-value",
"LINKEDIN_MIN_INTERVAL": "your-value",
"LINKEDIN_MAX_PER_HOUR": "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。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"linkedin-api": {
"type": "stdio",
"command": "uvx",
"args": [
"linkedin-api-mcp"
],
"env": {
"LINKEDIN_COOKIE": "your-value",
"LINKEDIN_HEADLESS": "your-value",
"LINKEDIN_MIN_INTERVAL": "your-value",
"LINKEDIN_MAX_PER_HOUR": "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
- Your LinkedIn li_at session cookie. Optional if you have already stored it in the OS keyring with `linkedin-api-mcp auth`, which is the recommended route: this cookie is equivalent to being logged in…
LINKEDIN_HEADLESSenvRun the browser headless. Defaults to true; set to 0 to watch what it does.LINKEDIN_MIN_INTERVALenvMinimum seconds between LinkedIn actions. Defaults to 2.LINKEDIN_MAX_PER_HOURenvHard ceiling on LinkedIn actions per rolling hour. Defaults to 120. The server refuses past this rather than sleeping, so an agent in a loop is told to stop.
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10日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 JohannsenLum 验证,该账户拥有此仓库
- … 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 3702 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 3702 个服务器的 23% 更新
- 基础检查结果等于或优于此分类中其他 3702 个服务器的 100%
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 安全吗?
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。
它需要哪些密钥或代码?
你需要填写:LINKEDIN_COOKIE
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(1.0.1)于3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 Python (uv)。
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:↓ 每周下载量i★ 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
Google Analytics MCP
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
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-api-mcp
Disclaimer: This is an independent, community project. It is not affiliated with, authorized by, endorsed by, or sponsored by LinkedIn Corporation or Microsoft. "LinkedIn" is a registered trademark of LinkedIn Corporation and is used here only descriptively to identify the third-party service this software interoperates with.
An MCP server for LinkedIn. It drives a real, headless browser (patchright, an undetected fork of Playwright) using your own logged-in LinkedIn session cookie. There is no scraping API, no credential stuffing, no bypass of LinkedIn's login. Your agent gets 12 read tools (profiles, companies, jobs, posts, your inbox) and two write tools, kept deliberately separate: sending a message and sending a connection request. Every action goes through a single browser session, one at a time, paced against limits you control. See Safety below.
Documentation: [mcp.johannsenlum.com/linkedin](https://mcp.johannsenlum.com/linkedin)
Install (one-click)
Deeplinks exist for Cursor and VS Code only; no other client has a documented install-link format. These prefill the command below, nothing else needs filling in since the cookie lives in your OS keyring, not an environment variable.
All clients
| Client | Deeplink? |
|---|---|
| Claude Code | no, one-line command |
| Claude Desktop | no |
| Cursor | yes, above |
| VS Code | yes, above |
| Codex CLI | no |
| Zed | no |
| Windsurf | no (Windsurf only resolves servers in its own registry) |
Claude Code
claude mcp add linkedin -- uvx linkedin-api-mcp
Claude Desktop : claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
No one-click install exists for Claude Desktop (it installs .mcpb bundles, not deeplinks). Copy this JSON in via Settings → Developer → Edit Config:
{
"mcpServers": { "linkedin": { "command": "uvx", "args": ["linkedin-api-mcp"] } } }
Cursor : ~/.cursor/mcp.json
Fallback for the button above, or if you'd rather paste it directly:
{
"mcpServers": { "linkedin": { "command": "uvx", "args": ["linkedin-api-mcp"] } } }
VS Code : .vscode/mcp.json
Fallback for the button above, or if you'd rather paste it directly. Note VS Code uses a servers key, not mcpServers:
{
"servers": { "linkedin": { "type": "stdio", "command": "uvx", "args": ["linkedin-api-mcp"] } } }
Codex CLI : ~/.codex/config.toml
[mcp_servers.linkedin]
command = "uvx" args = ["linkedin-api-mcp"]
Codex CLI's config schema has changed across versions and this block is not independently verified against a live install. If it doesn't load, the reliable path is running uvx linkedin-api-mcp yourself and pointing Codex at whatever its current stdio-server config expects.
Zed : settings.json
No deeplink exists for Zed. Add this under context_servers in your Zed settings:
{
"context_servers": { "linkedin": { "source": "custom", "command": "uvx", "args": ["linkedin-api-mcp"] } } }
Windsurf : ~/.codeium/windsurf/mcp_config.json
No deeplink exists for Windsurf. It only resolves servers from its own registry, so this has to be pasted in manually via Windsurf Settings → MCP Servers → Edit raw config:
{
"mcpServers": { "linkedin": { "command": "uvx", "args": ["linkedin-api-mcp"] } } }
If you'd rather not rely on the keyring in a given client (a sandboxed environment, or CI), pass the cookie directly instead of running auth:
{
"mcpServers": { "linkedin": { "command": "uvx", "args": ["linkedin-api-mcp"], "env": { "LINKEDIN_COOKIE": "your-li_at-value" } } } }
Anywhere you do this, treat that config file with the same care as the cookie itself: don't commit it, and restrict its permissions.
Getting your session cookie
LinkedIn doesn't offer an API key for this kind of access, so the server uses the same session cookie your browser already holds.
- One-time: install the Chromium build the server drives.
uvx --from linkedin-api-mcp patchright install chromium
- Log in to linkedin.com in a normal browser.
- Open DevTools (
F12orCmd+Opt+I) → Application → Cookies →https://www.linkedin.com. - Find the row named
li_atand copy its Value.
[!WARNING]
**This cookie *is* your LinkedIn login.** Anyone who has it can act as you:
read your messages, message your connections, see everything your account can
see, without needing your password. It survives a password change, and it
cannot be revoked from any session list LinkedIn shows you. Never paste it
into a chat, a commit, an issue, a screenshot, or anywhere other than
linkedin-api-mcp auth.
- Store it:
uvx linkedin-api-mcp auth
Paste the value in when prompted; the terminal will not echo it back. By default it's stored in your OS keyring (Keychain, Windows Credential Manager, or Secret Service on Linux), never written to a config file.
- Verify LinkedIn accepts it before wiring up a client:
uvx linkedin-api-mcp --test
Prints the server's redacted configuration and confirms the session is live. It never prints the cookie itself.
Tools
| Tool | Description |
|---|---|
get_profile | Fetch a member's profile (headline, about, experience, education, skills) by URL or public identifier. |
get_my_profile | Fetch the profile of the account this server is logged in as. |
search_people | Search LinkedIn members by keyword. |
get_inbox | List recent message thread previews. |
get_conversation | Fetch the full message history of one thread, by id. |
search_conversations | Search your message threads by participant or keyword. |
send_message ✏️ | Write. Sends a real message to another member from your account. |
connect ✏️ | Write. Sends a real connection invitation to another member from your account. |
get_company | Fetch a company page (about, size, industry, recent posts). |
search_companies | Search LinkedIn companies by keyword. |
search_jobs | Search job postings by keyword and optional location. |
get_job | Fetch one job posting in full. |
search_posts | Search LinkedIn feed posts by keyword. |
linkedin_status | Check session validity and current usage against the rate limits in Safety. |
14 tools: 12 read, 2 write. send_message and connect are the only two that change anything, and both are visible to another real person the moment they run: there is no draft, preview, or undo step. Everything else only reads what your account can already see. Covered by 68 tests.
What's verified, and what isn't
This is a days-old project. Rather than claim everything works, here's what's actually been checked against a live account, and what hasn't.
| Status | Tool / behaviour | Note |
|---|---|---|
| Verified live | get_my_profile, get_profile, search_people, get_company, search_companies, search_jobs, search_posts, get_inbox | Called against a real account and returned real data. |
| Verified live | send_message ✏️ | A real message was sent, then the thread was read back to confirm it arrived. |
| Not yet verified | connect ✏️, get_conversation, search_conversations, get_job, linkedin_status | Implemented and tested, but not yet exercised against a live account by hand. |
| Known gap | conversation_id from get_inbox | Comes back null. LinkedIn binds inbox rows to in-memory JS objects rather than URLs, so there's no id to read out of the page. |
| Known gap | Reaction and comment counts on search_posts | Come back null. |
| Known gap | experience and education on get_profile | LinkedIn loads these sections only on scroll; they currently come back empty. |
Safety
- A serialised action queue. Every tool call, including
linkedin_status, passes through the same queue before it touches the browser: one action at a time, never in parallel. - A minimum interval and an hourly ceiling, both enforced, not just claimed:
| Setting | Default | Env var | Effect |
|---|---|---|---|
| Minimum interval between actions | 2 seconds | LINKEDIN_MIN_INTERVAL | Calls are paced against the previous one, not run back-to-back. |
| Actions per rolling hour | 120 | LINKEDIN_MAX_PER_HOUR | Once hit, further calls fail immediately with a rate_limited error rather than queueing or sleeping. |
The ceiling is local to this server: it exists to stop a looping agent from generating a burst of LinkedIn traffic, not because LinkedIn told us these numbers. Lowering them is always safe; raising them is you deciding you're willing to accept more risk than the defaults assume.
- Prompt-injection fencing on all scraped free text. Anything read off a LinkedIn page (a headline, an about section, a message) passes through your agent as data. It is fenced before your agent sees it, so text on a profile or in a message cannot pose as an instruction.
- The cookie lives in your OS keyring, not a config file, by default. See Getting your session cookie.
- `send_message` proves delivery before reporting success. It polls th
只显示了开头部分;其余内容请在仓库中阅读