LinkedIn MCP for OpenWorker

LinkedIn MCP for OpenWorker

Enables LinkedIn profile reads and post operations through a local-first MCP server, with OAuth token management and approval-friendly tools for OpenWorker.

Category
访问服务器

README

LinkedIn MCP for OpenWorker

A local-first LinkedIn MCP server for OpenWorker. It runs over stdio, keeps tokens in environment variables or explicit tool inputs, and exposes small, approval-friendly tools for LinkedIn profile reads and post operations.

Tools

  • linkedin_start_oauth_flow starts the browser OAuth flow, captures the localhost callback, exchanges the code, and stores the token locally.
  • linkedin_auth_status reports whether a stored token exists and when it expires.
  • linkedin_logout deletes the stored token.
  • linkedin_exchange_authorization_code exchanges an OAuth code and stores the token, for manual fallback flows.
  • linkedin_get_my_profile reads the authenticated member profile from /v2/userinfo.
  • linkedin_create_text_post publishes or drafts a text-only post through /rest/posts.
  • linkedin_get_post retrieves a post by URN.
  • linkedin_find_posts_by_author lists posts for a member or organization URN.

Setup

npm i linkedin-mcp-openworker

Create a LinkedIn developer app and request the products/scopes you need:

  • openid profile email for Sign In with LinkedIn using OpenID Connect.
  • w_member_social to publish as the authenticated member.
  • Organization posting requires LinkedIn-approved organization scopes such as w_organization_social.

OpenWorker supports MCP servers through Manage -> Integrations using the same mcpServers JSON format as Claude Desktop and Cursor. After building, add a server like this:

{
  "mcpServers": {
    "linkedin": {
      "command": "npm",
      "args": ["linkedin-mcp-openworker"],
      "env": {
        "LINKEDIN_CLIENT_ID": "paste-your-linkedin-client-id-here",
        "LINKEDIN_CLIENT_SECRET": "paste-your-linkedin-client-secret-here",
        "LINKEDIN_REDIRECT_URI": "http://127.0.0.1:33333/linkedin/oauth/callback",
        "LINKEDIN_VERSION": "202607"
      }
    }
  }
}

LINKEDIN_VERSION defaults to 202607, matching LinkedIn Marketing API versioning guidance current at the time this project was created.

OAuth Flow

  1. In your LinkedIn developer app, add this authorized redirect URL:
http://127.0.0.1:33333/linkedin/oauth/callback
  1. Add the MCP server to OpenWorker with LINKEDIN_CLIENT_ID, LINKEDIN_CLIENT_SECRET, and LINKEDIN_REDIRECT_URI.
  2. Ask OpenWorker to run linkedin_start_oauth_flow.
  3. The MCP starts a localhost callback server, opens your browser to LinkedIn, validates the returned state, exchanges the authorization code, and stores the token at:
~/.linkedin-mcp-openworker/token.json
  1. After that, LinkedIn tools automatically use the stored token. Use linkedin_auth_status to inspect token status and linkedin_logout to delete it.

The default managed flow uses LinkedIn's regular 3-legged OAuth authorization endpoint:

https://www.linkedin.com/oauth/v2/authorization

That is the endpoint LinkedIn documents for OpenID Connect. It requests openid profile email w_member_social by default, exchanges the authorization code with your client_secret, and stores the returned access token and ID token metadata locally. Do not use auth_method: "pkce" with OpenID scopes; LinkedIn rejects that combination with Open ID permission is not supported for PKCE flows.

LinkedIn's general 3-legged OAuth documentation says redirect URLs should be HTTPS. If LinkedIn rejects the localhost callback URL for your app, use an HTTPS callback/tunnel URL that forwards to this machine and set LINKEDIN_REDIRECT_URI to the exact URL registered in the LinkedIn Developer Portal.

By default, OAuth tools redact tokens in tool results. Pass return_access_token: true only when you explicitly want a result to include token values.

Notes

LinkedIn API access depends on the products approved for your developer app. A token without w_member_social cannot publish member posts, and organization posts require organization permissions plus an authenticated member with the right page role.

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
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
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
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