Updated March 2026

Install LinkedIn MCP Server

Pick your client, copy the command, done.

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal

git clone https://github.com/eliasbiondo/linkedin-mcp-server.git
cd linkedin-mcp-server
uv sync

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal

claude mcp add linkedin-mcp-server -- node "<FULL_PATH_TO_LINKEDIN_MCP_SERVER>/dist/index.js"

Replace <FULL_PATH_TO_LINKEDIN_MCP_SERVER>/dist/index.js with the actual folder you prepared in step 1.

Available Tools (7)

Once configured, LinkedIn MCP Server gives your AI agent access to:

get_person_profileRetrieves detailed profile information for a specific person.

profile_urlsections

search_peopleSearches for people on LinkedIn based on query parameters.

query

get_company_profileRetrieves detailed profile information for a specific company.

company_url

get_company_postsRetrieves recent posts from a company page.

company_url

get_job_detailsRetrieves full details for a specific job listing.

job_url

search_jobsSearches for job listings based on filters.

querydate_postedjob_typeexperience_levelwork_typeeasy_applysort_by

close_browserCloses the active browser instance.

After setup, try these prompts with your AI agent:

→Search for software engineering jobs in London posted in the past week.

→Get the professional experience section for the profile at [URL].

→Find recent posts from the company page at [URL].

→Search for people with the title 'Product Manager' in San Francisco.

Save the docs, env vars, and workflow around LinkedIn MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.