linkedin-mcp

active

LinkedIn for AI assistants (MCP) — profiles, people/job/company search, feed & messaging as structured JSON, plus gated writes (connect/message/post/react/comment) via LinkedIn's API instead of DOM-clicking. Stealth-browser engine, 24 tools, built-in safety layer. Claude · Cursor · any MCP client.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository: github.com/devag7/linkedin-mcp
Package: npm: linkedin-mcp-tools
Run (stdio): npx -y linkedin-mcp-tools
The usual command for this package registry; check the repository README for required settings.
License: MIT
Last update: 2026-11-12
GitHub stars: ★ 12
Homepage: github.com/devag7/linkedin-mcp#readme

ai ai-agents anthropic automation claude claude-mcp cursor linkedin linkedin-api mcp mcp-server model-context-protocol

Listed in

github · source

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.