linkedapi

MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio linked-api-linkedapi-mcp node server.js \
  --env ENVIRONMENT="production" \
  --env LINKEDAPI_CLIENT_ID="your LinkedIn API client ID or placeholder" \
  --env LINKEDAPI_REDIRECT_URI="your OAuth redirect URI or placeholder" \
  --env LINKEDAPI_CLIENT_SECRET="your LinkedIn API client secret or placeholder"

How to use

Linked API MCP connects your LinkedIn account to AI assistants so they can perform LinkedIn-related tasks through a cloud browser. With this MCP server, your assistants can search for leads, analyze profiles, draft messages, and manage outreach across tools like Claude, Cursor, and VS Code. Typical workflows include asking the AI to find software engineers at mid-sized San Francisco companies, review their LinkedIn profiles, and generate personalized outreach messages. The system also supports recruitment and market research use cases, such as identifying candidates with specific skills or gathering company activity data to inform strategy. Tools are exposed by the MCP server and can be invoked from supported AI assistants; refer to the Available tools guide for the exact capabilities and how to call each tool.

How to install

Prerequisites:

Node.js (LTS) installed on your machine
Access to a LinkedIn account with the necessary permissions for the Linked API integration

Installation steps:

Clone the repository: git clone https://github.com/Linked-API/linkedapi-mcp.git cd linkedapi-mcp
Install dependencies: npm install
Configure environment variables (create a .env file or provide via your runtime environment): LINKEDAPI_CLIENT_ID=your_client_id LINKEDAPI_CLIENT_SECRET=your_client_secret LINKEDAPI_REDIRECT_URI=https://yourapp.example.com/oauth/callback ENVIRONMENT=production
Start the MCP server: node server.js
Verify the server is running and listening for requests on the configured port (default port depends on server.js).

Additional notes

Tips and notes:

Ensure your LinkedIn OAuth credentials are valid and the redirect URI matches what you’ve configured in the LinkedIn developer console.
The MCP server uses a cloud browser to perform LinkedIn actions; respect LinkedIn’s terms of service and rate limits to avoid account restrictions.
If you run into authentication issues, re-check the client secret, refresh tokens, and ensure the environment variables are correctly loaded.
For deployment, consider using a process manager (e.g., pm2) and securing endpoint access behind authentication.
The available tools are exposed to supported AI assistants; consult the Available tools documentation for each tool’s capabilities, limits, and typical prompts.
If you plan to customize tool behavior, you may need to adjust OAuth scopes and API permissions on the LinkedIn developer portal.

Related MCP Servers

context7

47.3k

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

obsidian -tools

612

Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.

MiniMax -JS

105

Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.

Model Context Protocol (MCP) server for LinkedIn API integration

mcp-bundler

Is the MCP configuration too complicated? You can easily share your own simplified setup!

akyn-sdk

Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.