linkedin-pages-mcp

linkedin-pages-mcp

MCP server for LinkedIn Company Page analytics, providing follower growth, demographics, page views, and engagement stats via the Community Management API.

Category
访问服务器

README

linkedin-pages-mcp

npm version License: MIT

MCP server for LinkedIn organization (Company Page) analytics via LinkedIn's Community Management API — follower growth and demographics, page views, post/share engagement, and video stats, surfaced to your AI assistant for analysis the native dashboard can't do.

Built for Claude Code and any MCP-compatible AI tool. Part of The SEO Engine toolkit by Lantern Row.

Scope & data policy

This server is intentionally read-only and limited to aggregate Page reporting data — the category LinkedIn permits storing for up to a year. It does not retrieve individual member-level data (who liked/commented and their profiles), which LinkedIn restricts to short-lived, in-app-only display and prohibits exporting. Keeping to aggregate Page metrics is both the compliant path and the genuinely useful one for trend analysis. There are no posting/write tools.

Access requirements (important)

Unlike most MCPs, this needs an approved LinkedIn developer app:

  1. A LinkedIn developer app owned by a registered business, associated with and verified by your Company Page.
  2. Approval for the Community Management API (Development tier to build, Standard tier for production — the latter requires a screencast demo).
  3. A Page admin completes the 3-legged OAuth flow to produce an access token.

See LinkedIn's app review process. Organic Page analytics is a supported use case; there is no follower minimum or partner-status gate, but approval is a manual review.

Configuration

{
  "mcpServers": {
    "linkedin-pages": {
      "command": "npx",
      "args": ["-y", "linkedin-pages-mcp"],
      "env": {
        "LINKEDIN_ACCESS_TOKEN": "your_3legged_member_token",
        "LINKEDIN_CLIENT_ID": "your_app_client_id",
        "LINKEDIN_CLIENT_SECRET": "your_app_client_secret",
        "LINKEDIN_REFRESH_TOKEN": "your_refresh_token",
        "LINKEDIN_ORGANIZATION_ID": "1234567"
      }
    }
  }
}

LINKEDIN_ACCESS_TOKEN is the only hard requirement; the client id/secret/refresh trio enables automatic token refresh (access tokens last ~60 days).

Tools

Tool Description
check_connection Verify the token; list Company Pages you administer.
list_organizations Company Pages the authenticated member can manage.
get_organization Page profile + total follower count.
get_follower_statistics Follower growth + demographic breakdowns (seniority, function, industry, size, geo).
get_page_statistics Page views / unique visitors by section and device.
get_share_statistics Organic post impressions, clicks, reactions, comments, shares, engagement rate.
list_posts An organization's posts (content + metadata).
refresh_token Mint a fresh access/refresh token pair to persist into your .env.

Statistics tools accept an optional start_ms/end_ms time range with DAY/WEEK/MONTH granularity; omit the range for lifetime/aggregate figures.

Notes

  • Versioned API: requests send Linkedin-Version (default 202606). LinkedIn sunsets versions roughly yearly — bump LINKEDIN_VERSION when migrating.
  • Security: credentials come from environment variables only; the bearer token is never logged.

License

MIT © Lantern Row

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
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
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
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