Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/o2alexanderfedin/linkedin-mcpRegister it in Claude Code
claude mcp add -e "LINKEDIN_CREDENTIALS=${LINKEDIN_CREDENTIALS}" linkedin-mcp -- uv --directory "<LOCAL_PATH>" run linkedin.pyReplace any placeholder paths in the command with the real path on your machine.
LINKEDIN_CREDENTIALSMake your agent remember this setup
linkedin-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Fetch user profiles including name, headline, and current position
- Advanced job search with filters for location, experience, and job type
- Retrieve LinkedIn feed posts with pagination support
- Parse and extract structured data from PDF resumes
Tools 4
get_profileFetch user profiles and extract key information such as name, headline, and current position.search_jobsAdvanced job search functionality with multiple parameters like location, experience level, and job type.get_feed_postsRetrieve LinkedIn feed posts with configurable limit and offset for pagination.parse_resumeParse and extract information from PDF resumes including contact details, skills, and experience.Environment Variables
LINKEDIN_CREDENTIALSrequiredCredentials required for accessing the LinkedIn API.Try it
Original README from o2alexanderfedin/linkedin-mcp
MCP Server for LinkedIn
A Model Context Protocol (MCP) server for linkedin to apply Jobs and search through feed seamlessly.
This uses Unoffical Linkedin API Docs for hitting at the clients Credentials.
Features
Profile Retrieval
Fetch user profiles using
get_profile()function Extract key information such asname,headline, andcurrent positionJob Search
- Advanced job search functionality with multiple parameters:
- Keywords
- Location
- Experience level
- Job type (Full-time, Contract, Part-time)
- Remote work options
- Date posted
- Required skills
- Customizable search limit
- Feed Posts
- Retrieve LinkedIn feed posts using
get_feed_posts() - Configurable limit and offset for pagination
- Resume Analysis
- Parse and extract information from
resumes (PDF format) - Extracted data includes:
- Name
- Phone number
- Skills
- Work experience
- Education
- Languages
Configuration
After cloning the repo, adjust the <LOCAL_PATH> accordingly
{
"linkedin":{
"command":"uv",
"args": [
"--directory",
"<LOCAL_PATH>",
"run",
"linkedin.py"
]
}
}
Usage
I have been testing using MCP-client and found as the best one for testing your MCP-Servers.