kaushik-linkedin-mcp
Enables Claude AI to interact with LinkedIn through browser automation, including profile reading, people and job search, company research, post publishing, and profile editing.
README
🔗 kaushik-linkedin-mcp
A personal LinkedIn MCP server — built from scratch. Not a fork. Not a clone. Written by Kaushik Muthukumaran.
This MCP server connects Claude AI directly to LinkedIn using browser automation. It gives Claude 8 tools to read profiles, search people and jobs, get company data, publish posts, edit your profile, and manage sessions — all from a conversation with Claude.
📖 Table of Contents
- What You Can Do With This
- How to Clone and Run It
- Project Structure
- How It Works
- Tools Reference
- For People Cloning This Repo
- Security
- Troubleshooting
- Author
🚀 What You Can Do With This
Once connected to Claude, you can have natural conversations that do real LinkedIn actions.
✏️ Edit Your LinkedIn Profile By Just Telling Claude
Method 1 — Tell Claude your details in chat:
"Change my headline to: Security Engineer | Zero Trust | CrowdStrike | 14K+ Endpoints" "Add a new job: Security Engineer at MasTec, promoted after 1 year" "Update my Sankara Nethralaya role to focus on vulnerability assessments and OSINT"
Claude opens Chrome, finds the right field, types your content, and saves it.
Method 2 — Upload your resume and ask Claude to sync it:
"Here's my updated resume — update my LinkedIn to match it"
Claude reads every section, compares it to your LinkedIn, and edits each section one by one.
Supports: .pdf, .docx, .txt
Method 3 — Targeted corrections mid-conversation:
"Split my MasTec role into two entries at August 2025" "Add OSINT and CyberArk to my skills" "Move Sankara Nethralaya from Part-time to Full-time"
👤 Profile Intelligence
"Pull Kaushik's full LinkedIn profile including experience and skills" "Show me their recent posts and engagement"
Reads: name, headline, location, connections, about, full experience, education, skills, posts, contact info.
🔍 People Search
"Find Security Engineers at CrowdStrike in Pennsylvania" "Search for CISOs in the healthcare industry"
Returns: name, headline, location, username, profile URL. Max 100 results per call.
💼 Job Search & Research
"Find Senior Security Engineer jobs in Pennsylvania posted this week" "Show me remote Zero Trust architect roles — mid-senior level only" "What's the salary range for this CrowdStrike job?"
Full LinkedIn job search: date posted, experience level, job type, work arrangement, Easy Apply.
🏢 Company Research
"What does CrowdStrike's LinkedIn page say about them?" "Show me MasTec's recent posts and engagement numbers" "What roles is Microsoft hiring for right now?"
Returns: about, industry, size, headquarters, recent posts with reactions, open roles.
📢 Post Publishing
"Publish my vulnerability management post to LinkedIn" "Post this Zero Trust insight with these hashtags"
Navigates to feed, opens composer, injects text securely, clicks Post, confirms success.
🤖 Combined Power Workflows
"Search for Senior Security Engineer jobs at CrowdStrike, get the top 3 JDs, and tell me exactly how my resume matches each one"
"Find Security Engineers at my target companies and draft a personalised connection message for each one based on their background"
"Write and publish a post about today's Rapid7 CVE findings — under 200 words with 5 hashtags"
🖥️ How to Clone and Run It
Step 1 — Install Homebrew
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
echo 'eval "$(/opt/homebrew/bin/brew shellenv zsh)"' >> ~/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv zsh)"
Step 2 — Install Node.js and Git
brew install node git
Step 3 — Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env
⚠️ Save the path from
which uv— you'll need it for Claude Desktop config.
Step 4 — Clone and Install
git clone https://github.com/Secure-tree/kaushik-linkedin-mcp
cd kaushik-linkedin-mcp
uv sync
uv run playwright install chromium
Step 5 — Authenticate with LinkedIn
uv run kaushik-linkedin-mcp --login
A Chrome window opens. Log in to your LinkedIn. Session saves automatically.
Step 6 — Verify Session
uv run kaushik-linkedin-mcp --status
# Status: Valid ✅
Step 7 — Connect to Claude Desktop
Open: ~/Library/Application Support/Claude/claude_desktop_config.json
Merge this in:
{
"mcpServers": {
"linkedin": {
"command": "/Users/YOUR_USERNAME/.local/bin/uv",
"args": [
"--directory",
"/Users/YOUR_USERNAME/kaushik-linkedin-mcp",
"run",
"kaushik-linkedin-mcp"
]
}
}
}
⚠️ Use the full path to
uvfromwhich uv— Claude Desktop does not inherit your terminal PATH.
Restart Claude:
pkill -f Claude && sleep 2 && open /Applications/Claude.app
🏗️ Project Structure
kaushik-linkedin-mcp/
├── pyproject.toml # Project config, CLI entry point, dependencies
├── .python-version # Pins Python 3.12
├── .env.example # Config template — copy to .env
├── .gitignore # Protects session data and .env
├── LICENSE # MIT
└── src/
└── kaushik_linkedin_mcp/
├── __init__.py
├── server.py # FastMCP server — all 8 tools
├── browser.py # Playwright session manager
└── tools/
├── profile.py # get_person_profile
├── jobs.py # search_jobs + get_job_details
├── posts.py # publish_linkedin_post
└── search.py # search_people + get_company_profile
⚙️ How It Works
You (in Claude chat)
│
│ "Search for Security Engineer jobs in Pennsylvania"
▼
Claude Desktop
│ stdio (local process)
▼
kaushik-linkedin-mcp (Python / FastMCP)
│ Playwright browser automation
▼
Chromium (headless, on your Mac)
│ HTTPS — your authenticated session
▼
LinkedIn.com → returns structured JSON back to Claude
Note for cloners: Session saves to
~/.kaushik-linkedin-mcp/session/storage.jsonon YOUR machine. The author has zero access to your account.
🧰 Tools Reference
| Tool | Parameters |
|---|---|
get_person_profile |
linkedin_username, sections (main/experience/education/skills/posts/contact) |
search_linkedin_people |
keywords, location, max_results (1–100) |
search_linkedin_jobs |
keywords, location, date_posted, experience_level, job_type, work_type, easy_apply, max_pages |
get_linkedin_job_details |
job_id |
get_linkedin_company |
company_name, sections (about/posts/jobs) |
publish_linkedin_post |
text |
check_session_status |
— |
close_browser |
— |
👥 For People Cloning This Repo
When you clone and run this, you log into your own LinkedIn — not the author's.
| Thing | Change Required |
|---|---|
--login step |
Log in with YOUR LinkedIn credentials |
| Claude Desktop config | Update path to YOUR clone location and uv path |
.env |
Optional — defaults work for most setups |
pyproject.toml author |
Leave as-is — this is the author's name |
Quick start:
git clone https://github.com/Secure-tree/kaushik-linkedin-mcp
cd kaushik-linkedin-mcp
uv sync
uv run playwright install chromium
uv run kaushik-linkedin-mcp --login
uv run kaushik-linkedin-mcp --status
🔐 Security
| Check | Status |
|---|---|
| No hardcoded credentials | ✅ |
| No JS template literal injection | ✅ User values passed via CDP args |
| Input validation | ✅ max_results clamped 1–100 |
| Session stored outside repo | ✅ ~/.kaushik-linkedin-mcp/ |
.env never committed |
✅ In .gitignore |
| No shell/subprocess calls | ✅ |
| No 3rd party API calls | ✅ Only linkedin.com |
| Local stdio communication | ✅ No network exposure |
🔧 Troubleshooting
No LinkedIn tools in Claude
→ Use full uv path in config: which uv → /Users/YOU/.local/bin/uv
Status: Expired/Invalid
→ uv run kaushik-linkedin-mcp --logout && uv run kaushik-linkedin-mcp --login
npm install fails
→ This is Python. Use uv sync not npm install.
Config has two {} blocks
→ Merge into one root object: { "preferences": {...}, "mcpServers": {...} }
⚡ Quick Reference
# Setup
git clone https://github.com/Secure-tree/kaushik-linkedin-mcp
cd kaushik-linkedin-mcp && uv sync
uv run playwright install chromium
uv run kaushik-linkedin-mcp --login
uv run kaushik-linkedin-mcp --status
# Restart Claude after config changes
pkill -f Claude && sleep 2 && open /Applications/Claude.app
# Re-authenticate
uv run kaushik-linkedin-mcp --logout && uv run kaushik-linkedin-mcp --login
👤 Author
Kaushik Muthukumaran Security Engineer | AI + Cybersecurity Researcher
- 📧 kaushikrmk01@gmail.com
- 🏅 Ms in Cybersecurity
- 🏅 CompTIA Network+ Certified
- 🔬 Research: AI-Driven Threat Detection · Zero Trust · ML Risk Scoring and Remediation
📄 License
MIT License — see LICENSE for details.
Built with Claude AI (Anthropic) · FastMCP · Playwright · Python 3.12
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。