LinkedInMCP: Revolutionizing LinkedIn API Interactions
🚀 Comprehensive Setup Guide
Prerequisites
- Node.js 16+
- LinkedIn Developer Account
- MCP-Compatible LLM (Claude, OpenAI, etc.)
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Model Context Protocol (MCP) server for LinkedIn API integration
This MCP server talks to LinkedIn's official HTTP APIs. Several things people run into are LinkedIn product / partner restrictions, not bugs in the install steps:
client_credentials (2-legged OAuth) is not available to most developer apps.
LinkedIn docs state that apps cannot mint application tokens by default. A standard app that posts grant_type=client_credentials typically gets:
access_denied / "This application is not allowed to create application tokens".
That flow is reserved for approved LinkedIn enterprise / partner products. You usually need to contact a LinkedIn Relationship Manager or Business Development contact, or use the member authorization-code (3-legged) flow instead. See Client Credential Flow (2-legged OAuth).
There is no public general people-search endpoint at /search/people.
LinkedIn does not document a free, unrestricted "search any member by keyword / company / location" API for ordinary developer apps. The search-people tool in this repo currently calls /v2/search/people, which is not a documented public endpoint and will not work with a standard developer token.
What LinkedIn does document today is limited profile / people APIs (mostly for the authenticated member) and a restricted People Typeahead API for organization-page @mention search of page followers (docs). Broader people search requires a relevant LinkedIn partner product (for example Talent / Sales). Treat search-people as experimental / partner-only until this server is updated to a documented endpoint.
Send credentials in the POST body, never in the URL.
Token requests now use Content-Type: application/x-www-form-urlencoded with client_id / client_secret in the body, matching LinkedIn's OAuth guidance, so secrets are not appended as query parameters.
Important: For detailed instructions on obtaining access tokens and authentication for LinkedIn API, refer to the official documentation: Getting Access to LinkedIn API
git clone https://github.com/Dishant27/linkedin-mcp-server.git
cd linkedin-mcp-server
npm install
.env FileCreate a .env file in the project root:
LINKEDIN_CLIENT_ID=your_client_id_here
LINKEDIN_CLIENT_SECRET=your_client_secret_here
claude_desktop_config.json (for Claude Desktop){
"mcpServers": {
"linkedin": {
"command": "node",
"args": ["/absolute/path/to/linkedin-mcp-server/dist/index.js"],
"env": {
"LINKEDIN_CLIENT_ID": "your_client_id",
"LINKEDIN_CLIENT_SECRET": "your_client_secret"
}
}
}
}
{
"tools": [
{
"name": "search-people",
"description": "Search for LinkedIn profiles",
"parameters": {
"type": "object",
"properties": {
"keywords": {
"type": "string",
"description": "Keywords to search for in profiles"
},
"currentCompany": {
"type": "array",
"items": {"type": "string"},
"description": "Filter by current company"
},
"industries": {
"type": "array",
"items": {"type": "string"},
"description": "Filter by industries"
},
"location": {
"type": "string",
"description": "Filter by location"
}
}
}
},
{
"name": "get-profile",
"description": "Retrieve detailed LinkedIn profile information",
"parameters": {
"type": "object",
"properties": {
"publicId": {
"type": "string",
"description": "Public ID of the LinkedIn profile"
},
"urnId": {
"type": "string",
"description": "URN ID of the LinkedIn profile"
}
}
}
}
]
}
npm run build
npm start
> Find software engineers in San Francisco working at tech companies
# The LLM will use the search-people tool to:
# 1. Search LinkedIn profiles
# 2. Filter by location (San Francisco)
# 3. Filter by industry (Technology)
# 4. Return relevant profile details
Check out the detailed article explaining the concept and implementation:
LinkedInMCP is an innovative Model Context Protocol (MCP) server designed to transform how developers interact with LinkedIn's API. Born from the need for more flexible and powerful LinkedIn data integration, this project provides a robust, extensible framework for advanced LinkedIn data retrieval and interaction.
Recognizing the limitations of traditional LinkedIn API approaches, this solution creates a more intelligent, context-aware method of working with professional network data.
LinkedInMCP enables powerful applications for business settings:
The comprehensive security model of LinkedInMCP implements multiple layers of protection:
linkedin-mcp-server/
│
├── src/
│ ├── index.ts # Main server entry point
│ ├── auth.ts # LinkedIn authentication handler
│ └── client.ts # LinkedIn API interaction client
│
├── dist/ # Compiled JavaScript files
│ ├── index.js
│ ├── auth.js
│ └── client.js
│
├── .env # Secret environment variables
├── .env.example # Template for environment variables
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # Project documentation
Inspired by the project? Contributions are welcome!
Distributed under the MIT License.
Disclaimer: This project is an independent innovation and is not officially affiliated with LinkedIn or Microsoft.
Model Context Protocol (MCP) server for LinkedIn API integration
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Linkedin ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-27 Model Context Protocol (MCP) server for LinkedIn API integration