LinkedIn Influencer MCP 🚀
🎯 A powerful MCP server for automating LinkedIn interactions and content analysis
🏗️ Architecture
📖 Overview
This Model Context Protocol (MCP) server provides tools and resources for automating sending linkedin connection requests, analyzing profiles, and scraping content and posting content. Built with FastMCP, it enables Claude to perform complex LinkedIn operations. We plan on adding a lot more in future based on feedback.
✨ Features
👤 Profile Analysis
- Extract comprehensive LinkedIn profile data including name, headline, experience, education
- Analyze profile strength and engagement metrics
- Track profile changes over time
- Generate insights about professional background
📝 Content Management
- Create and schedule LinkedIn posts with optimal timing
- Scrape and analyze posts from target profiles
- Track post performance and engagement
- Generate content from YouTube video transcripts
- Repurpose content across platforms
🤝 Network Building
- Send personalized connection requests at scale
- Search and connect with specific professional groups
- Automated recruiter outreach with customized messaging
- Track connection request status and responses
- Build targeted professional networks
✍️ Content Generation
- AI-powered post creation using multiple LLM options
- Content repurposing from various sources (YouTube, articles, etc.)
- Writing style mimicking based on successful profiles
- SEO optimization for maximum visibility
- Hashtag optimization and trend analysis
🛠️ Automation Tools
- Headless browser automation with Playwright
- Robust session management and cookie handling
- Rate limiting protection
- Comprehensive error handling and recovery
- Detailed logging and monitoring
🔧 Available Tools
# Get profile information
await get_linkedin_profile_info(linkedin_profile_id="profile_id")
# Scrape posts
await get_linkedin_profile_posts(linkedin_profile_id="profile_id", max_posts=5)
# Create a post
await create_linkedin_post(content="Your post content")
# Send connection requests
await send_linkedin_connection_requests(connection=ConnectionRequest(...))
📋 Prompt Templates
connection_requests_to_recruiters_prompt: Generate personalized outreach messages to recruitersconnection_requests_with_custom_note: Create tailored connection requestsresearch_and_create_post: Research and generate authentic LinkedIn posts (Requires Brave MCP)scrape_linkedin_posts_and_post_to_linkedin: Analyze and create content from influencerscreate_linkedin_post_from_youtube: Convert YouTube content into LinkedIn posts (requires youtube transcript MCP)
⚙️ Configuration
To add this tool as an MCP server, modify your Claude desktop configuration file:
- MacOS:
~/Library/Application\ Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
{
"linkedin-influencer-mcp": {
"command": "uv",
"args": ["run", "linkedin-influencer-mcp"],
"env": {
"LINKEDIN_EMAIL": "your email",
"LINKEDIN_PASSWORD": "your password",
"GROQ_API_KEY": "GROQ API KEY, for generating custom note",
"USER_LINKEDIN_PROFILE_ID": "your linkedin profile ID",
"GOOGLE_API_KEY": "OPTIONAL: IF GROQ API rate limit is reached, use google",
"OPENAI_API_KEY": "OPTIONAL: IF you need more requests,use openai"
}
}
}
🎯 Use Cases
Example #1: Automated Recruiter Outreach
Use the recruiter outreach template to automatically connect with relevant recruiters:
Example prompt to Claude:
Connect with tech recruiters in the San Francisco Bay Area who are hiring for senior software engineering roles. Personalize the message based on my experience with Python and distributed systems.
Example #2: Content Creation from Research
Use the research and post creation template to generate engaging content:
Example prompt:
Research the latest trends in AI and create a LinkedIn post about the impact of large language models on software development. Include relevant statistics and tag key influencers in the space.
📚 Documentation
For development setup and contribution guidelines, please see DEVELOPMENT.md
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
Metadata
Release files for linkedin-influencer-mcp 0.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| linkedin_influencer_mcp-0.1.8.tar.gz | 20.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| linkedin_influencer_mcp-0.1.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 42.2 kB
Release files / linkedin_influencer_mcp-0.1.8.tar.gz
| Download URL | linkedin_influencer_mcp-0.1.8.tar.gz |
|---|---|
| Size | 20.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
43c1a9d9103e611b5bc1a69f8067a9a14e9bbeebaaa04bebddd56cec95a7a92d
|
|
BLAKE2b-256 checksum How to use checksums |
04c3eb8890146f6991bddaf6df361bd0f8adb93d3558f9c411bbe31b0f5f5cdc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.2
|
Release files / linkedin_influencer_mcp-0.1.8-py3-none-any.whl
| Download URL | linkedin_influencer_mcp-0.1.8-py3-none-any.whl |
|---|---|
| Size | 22.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
12d9889823bfc33601d66beb0deaa3f1f0af7c7ecd1202cda93a18e06f6ed5ba
|
|
BLAKE2b-256 checksum How to use checksums |
0948cb35ea403e7ce7be7c04d751fcc5a58d8afda6703ba14d7bfd6dcc5d157d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.2
|
Security for linkedin-influencer-mcp 0.1.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.