linkedin-marketing-mcp
Automates LinkedIn B2B marketing tasks such as profile search, company analysis, and connection request drafting, with optional AI-powered features via DeepSeek.
README
LinkedIn Marketing MCP v1.0.0
Free MCP server to automate LinkedIn B2B marketing β search profiles, draft connection requests, analyze companies. Premium features powered by DeepSeek AI.
π Quick Start (FREE, no API key needed)
# Install
npm install -g linkedin-marketing-mcp
# Add to your MCP client (e.g., Cline, Claude Desktop)
# No API key needed for FREE features!
node /path/to/linkedin-marketing-mcp/index.js
That's it! Start using these FREE tools immediately:
search_public_profilesβ Find LinkedIn profiles by keyword (via Google search)analyze_companyβ Analyze a LinkedIn company page (public data)draft_connection_requestβ Template-based connection request drafts
π§ FREE Features (no API key)
| Tool | What it does | No API key? |
|---|---|---|
search_public_profiles |
Search for LinkedIn profiles (via Google) | β Works immediately |
analyze_company |
Analyze company page (public data) | β Works immediately |
draft_connection_request |
Draft a connection request (template) | β Works immediately |
π PREMIUM Features (requires DeepSeek API key)
Set DEEPSEEK_API_KEY in your .env file to unlock:
| Tool | What it does | Why it's worth paying for |
|---|---|---|
optimize_linkedin_post |
AI-optimizes your LinkedIn post for max engagement | 10x more engagement |
generate_prospecting_list |
AI generates a prospect list based on your ICP | Save 10+ hours/week |
draft_connection_request (AI mode) |
AI-personalized connection requests | 3x higher acceptance rate |
Get a DeepSeek API key: https://platform.deepseek.com (cheap, ~$0.14/1M tokens)
π¦ Installation
For MCP Client Users (Claude Desktop, Cline, etc.)
Add to your MCP client config:
{
"mcpServers": {
"linkedin-marketing": {
"command": "node",
"args": ["/path/to/linkedin-marketing-mcp/index.js"],
"env": {
"DEEPSEEK_API_KEY": "sk-xxx" // Optional, for premium features
}
}
}
}
For Developers
git clone https://github.com/1036007003-wq/linkedin-marketing-mcp.git
cd linkedin-marketing-mcp
npm install
node index.js
π― Use Cases
1. Find potential customers on LinkedIn
Use `search_public_profiles` with keyword "AI engineer"
β Returns: Google search query to find AI engineers on LinkedIn
2. Research a target company
Use `analyze_company` with company name "OpenAI"
β Returns: Checklist to analyze OpenAI's LinkedIn company page
3. Draft a non-salesy connection request
Use `draft_connection_request`
β Returns: Template-based message (or AI draft with DeepSeek)
4. (Premium) Optimize your LinkedIn post
Use `optimize_linkedin_post`
β Returns: AI-optimized post (hook, hashtags, best posting time)
5. (Premium) Generate a prospecting list
Use `generate_prospecting_list` with ICP description
β Returns: AI-generated list of 10 prospects with outreach angles
π For China Users (δΈε½η¨ζ·)
# If you can't access LinkedIn directly:
# 1. Set proxy
export HTTP_PROXY=http://127.0.0.1:7890
export HTTPS_PROXY=http://127.0.0.1:7890
# 2. Or use a China-friendly API proxy
# (We recommend setting up your own proxy, or use a VPN)
π Why This is Better Than...
| Alternative | Problem | Our Solution |
|---|---|---|
| Manual LinkedIn research | Takes hours, boring | Automated in seconds |
| LinkedIn Sales Navigator | $99/month | Free basic features |
| Hiring a BDR (Business Development Rep) | $4000+ / month | One-time setup |
| Other LinkedIn tools | Require LinkedIn API (complicated) | No API needed for basic features |
π Roadmap
- [x] Free: Search public profiles (via Google)
- [x] Free: Analyze company (public data)
- [x] Free: Draft connection requests (template)
- [x] Premium: AI-powered post optimization (DeepSeek)
- [x] Premium: AI prospecting list generation
- [ ] Paid: Auto-connection request sender (with rate limiting)
- [ ] Paid: Profile view analytics dashboard
- [ ] Paid: Auto-post scheduler
π° Pricing (GitHub Sponsors)
| Tier | Price | What you get |
|---|---|---|
| Free | $0 | 3 basic tools (no API key needed) |
| Supporter | $5/mo | All premium features + priority support |
| Team | $25/mo | All premium + custom AI prompts + prospecting templates |
| One-time | $99 | Lifetime access (no subscription) |
π Sponsor here: https://github.com/sponsors/1036007003-wq
π Issues / Feature Requests
Open an issue: https://github.com/1036007003-wq/linkedin-marketing-mcp/issues
β Star History
Built by @1036007003-wq | Sponsor on GitHub β€οΈ
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.