mcp-linkedin and linkedapi-mcp

Both tools are independent MCP servers providing distinct, potentially overlapping, functionalities for interacting with LinkedIn, making them competitors as users would likely choose one over the other based on their specific needs for Feeds/Job API access or broader account control/real-time data retrieval.

mcp-linkedin
48
Emerging
linkedapi-mcp
44
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 10/25
Adoption 8/25
Maturity 15/25
Community 11/25
Stars: 194
Forks: 50
Downloads:
Commits (30d): 0
Language: Python
License: Unlicense
Stars: 44
Forks: 5
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stale 6m No Package No Dependents
No Package No Dependents

About mcp-linkedin

adhikasp/mcp-linkedin

A Model Context Protocol (MCP) server that provides tools to interact with LinkedIn's Feeds and Job API.

This helps professionals and job seekers automate their interactions with LinkedIn. You input commands, in plain language, to search for jobs, analyze job descriptions against your resume, or summarize recent posts from your feed. It outputs tailored job recommendations and summaries of LinkedIn activity, helping you stay informed and efficient without manual browsing.

recruitment career-development social-listening job-search professional-networking

About linkedapi-mcp

Linked-API/linkedapi-mcp

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

This tool connects your LinkedIn account to AI assistants like Claude or VS Code, allowing them to automate various tasks on your behalf. You can instruct your AI to search for leads, analyze profiles, draft messages, and gather market research data, with the AI handling the interactions and providing you with summarized information or drafted communications. Sales professionals, recruiters, and market researchers who use AI assistants will find this most useful.

sales-automation recruitment market-research lead-generation social-selling

Scores updated daily from GitHub, PyPI, and npm data. How scores work