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 LinkedInβs API.
- β¨ Human-style LinkedIn post generation with strict tone and structure guidelines
- π§ LangChain agent powered by OpenAI LLM (
gpt-4o) - π§© Modular MCP design: scalable and extendable with additional tools (e.g., X, Instagram)
- π§ Built-in LinkedIn posting tool via LinkedIn REST API
- π₯οΈ Streamlit frontend for clean user interaction
- π FastAPI backend for MCP logic orchestration
- Python β Core backend language
- Streamlit β Web application framework for UI
- FastAPI β Backend API layer for handling requests and MCP orchestration
- OpenAI GPT-4o β LLM used for generating high-quality, human-style LinkedIn posts
- LangChain β Agent framework for chaining prompt execution and tool usage
- LinkedIn REST API β Used to post directly to LinkedIn profiles
/project-root/
βββ streamlit_app/
β βββ app.py
βββ mcp_server/
β βββ main.py
β βββ agent_runner.py
β βββ llm/
β β βββ llm_config.py
β βββ agents/
β β βββ post_writer_agent.py
β βββ tools/
β βββ linkedin_poster.py
βββ .env
βββ requirements.txt
βββ README.md
π€ Vetrivel Maheswaran
Β© Created by Vetrivel Maheswaran

