LinkedIn MCP Server

The all-in-one MCP server for LinkedIn. Plug any AI agent — Claude, Cursor, ChatGPT, VS Code, or your own — into a single endpoint and pull live data from LinkedIn: full people profiles, company pages, posts, job listings, and people / job search.

What you get

• Full people profiles — name, headline, location, about, avatar and banner, follower and connection counts, current company, full work experience, education history, languages, certifications, recent activity, and bio links
• Company pages — name, logo, slogan, about, description, website, headquarters, locations, employee count on LinkedIn, follower count, company size, industries, specialties, founded year, employees showcase, and similar companies
• Posts and engagement — post text, hashtags, embedded links, images, videos, like and comment counts, post type, repost data, tagged companies and people, and author info; collect specific post URLs or discover all posts from a person or company
• Job listings — title, company, location, summary, seniority, employment type, industries, base pay range, applicant count, easy-apply flag, apply link, and job poster info
• People search — find LinkedIn profiles by name and pipe the URLs straight into get-profile for full enrichment
• Job search — keyword + location, filtered by country, time range, job type, experience level, remote/hybrid/onsite, and employer
• Bulk lookups — query up to 20 URLs in a single call for profiles, companies, posts, and jobs
• Saved media — profile pictures and company logos are saved to the run's Apify Key-Value Store and returned as permanent signed URLs (profilePicStorageUrl, logoStorageUrl)
• One endpoint, six tools — no glue code, no per-tool integrations, no scraping infrastructure to maintain

Use cases

• B2B sales prospecting — enrich a list of LinkedIn URLs with full profile data, current role, and seniority for outbound outreach
• Recruiting and sourcing — search by name or job keyword, then pull the full work history, education, and recent activity for every candidate
• Lead generation — build target lists by scraping company employees, then enrich each profile in bulk
• Competitive intelligence — track competitor headcount, hiring patterns, post engagement, and company updates
• Account research — pull the full picture for a target company before a sales call: size, industries, locations, and key employees
• Market and talent mapping — discover everyone with a given title in a region, then enrich with full profile data
• AI agents and assistants — give any LLM live LinkedIn access without building a custom scraper

Tools exposed

Tool	Returns
get-profile	Full people profile data for up to 20 LinkedIn /in/ URLs per call
get-company	Full company page data for up to 20 LinkedIn /company/ URLs per call
get-post	Post content + engagement; modes: by post URL, by profile URL, or by company URL
get-job	Full job listing details for up to 20 LinkedIn /jobs/view/ URLs per call
search-people	Search by name (max 50 names per call); returns matching profile URLs and snippets
search-jobs	Job search by keyword, location, country, time range, type, seniority, remote, company

How to use

Use Apify's hosted MCP gateway — it generates ready-to-paste config snippets for Claude Desktop, Cursor, VS Code, ChatGPT, and any other MCP-compatible client:

mcp.apify.com/?tools=seemuapps/linkedin-mcp

Open the link, sign in, and copy the snippet for your client.

Where to get your Apify API token

Go to console.apify.com/settings/integrations and copy your Personal API token. (Sign in or create a free account if you haven't already.)

The token authorizes calls to the MCP server and is what Apify uses to bill you for tool calls.

Pricing (pay-per-event)

Tool	Event	Charged
get-profile	profile	Once per profile successfully returned
get-company	company	Once per company page successfully returned
get-post	post	Once per post successfully returned
get-job	job	Once per job listing successfully returned
search-people	person-result	Once per matched person returned
search-jobs	job	Once per matching job returned

Failed calls are not charged. Partial failures (e.g. one bad URL in a batch) are reported per-item without aborting the whole call.

Notes

• LinkedIn data is fetched live; results reflect the public profile or page at the time of the call.
• Some calls may take 30 seconds to 2 minutes to return because the upstream provider runs an async snapshot — set generous timeouts in your MCP client.
• get-post in discoverByProfileUrl or discoverByCompanyUrl mode can return many posts per URL — cap with maxItems if you only want the latest few.
• search-people works best with reasonably distinctive names; common names will return a mix of matches that you'll want to disambiguate before calling get-profile.
• search-jobs returns up-to-date listings; pipe url from each result back into get-job for the full job description and metadata.