Linkedin Post Agent

This project is a powerful and modular AI agent system that generates and posts professional LinkedIn content using OpenAI and LangChain, built with a clean MCP architecture. It takes an input idea from the user, transforms it into a high-quality LinkedIn post using a custom prompt template, and posts it directly to the user's LinkedIn profile using LinkedIn’s API.

---

🚀 Features

• ✨ Human-style LinkedIn post generation with strict tone and structure guidelines
• 🧠 LangChain agent powered by OpenAI LLM (gpt-4o)
• 🧩 Modular MCP design: scalable and extendable with additional tools (e.g., X, Instagram)
• 🔧 Built-in LinkedIn posting tool via LinkedIn REST API
• 🖥️ Streamlit frontend for clean user interaction
• 🔄 FastAPI backend for MCP logic orchestration

---

📦 Tech Stack

• Python — Core backend language
• Streamlit — Web application framework for UI
• FastAPI — Backend API layer for handling requests and MCP orchestration
• OpenAI GPT-4o — LLM used for generating high-quality, human-style LinkedIn posts
• LangChain — Agent framework for chaining prompt execution and tool usage
• LinkedIn REST API — Used to post directly to LinkedIn profiles

---

📁 Project Structure

/project-root/
├── streamlit_app/
│ └── app.py
│
├── mcp_server/ 
│   ├── main.py 
│   ├── agent_runner.py 
│   ├── llm/
│   │   └── llm_config.py 
│   ├── agents/
│   │   └── post_writer_agent.py 
│   └── tools/
│       └── linkedin_poster.py 
├── .env 
├── requirements.txt 
└── README.md # 

---

⚙️ How to Run the Project

1. Clone the Repository

git clone https://github.com/vetrivel07/linkedin-post-agent.git
cd linkedin-agent

2. Create and Activate Virtual Environment

python -m venv venv

Windows

venv\Scripts\activate

macOS / Linux

source venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Configure Environment Variables

Create a .env file in the project root.

See Environment Variables section below for details.

Start the FastAPI Backend (MCP Server)

From the project root:

uvicorn mcp_server.main:app --host 0.0.0.0 --port 8000 --reload

Verify backend is running:

Open browser → http://localhost:8000/docs

Start the Streamlit Frontend

Open a second terminal, activate the same virtual environment, then:

streamlit run streamlit_app/app.py

The app will be available at:

http://localhost:8501

5. Generate & Post to LinkedIn

1. Enter your LinkedIn post idea in the UI
2. Click Generate & Post
3. The agent:
   • Generates a professional post using OpenAI
   • Posts it to LinkedIn using your authorized account

---

🔐 Environment Variables

Create a .env file in the project root with the following variables:

# OpenAI
OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxx

# LinkedIn OAuth (Application credentials)
LINKEDIN_ACCESS_TOKEN=your_access_token_here

# LinkedIn User Token (generated via OAuth)
LINKEDIN_URN=urn:li:person:your_urn_here

---

📸 Preview

---

Author

👤 Vetrivel Maheswaran

Connect With Me 🌐

© Created by Vetrivel Maheswaran