https://github.com/suyashsangale/mcp-server-client
A modular, open-source framework for building and deploying AI-powered tools and agent-based chat systems using MCP server and Streamlit App
https://github.com/suyashsangale/mcp-server-client
fastmcp generative-ai mcp mcp-client mcp-server rest-api streamlit
Last synced: about 2 months ago
JSON representation
A modular, open-source framework for building and deploying AI-powered tools and agent-based chat systems using MCP server and Streamlit App
- Host: GitHub
- URL: https://github.com/suyashsangale/mcp-server-client
- Owner: suyashsangale
- Created: 2025-06-20T11:45:35.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-20T12:22:35.000Z (about 1 year ago)
- Last Synced: 2025-06-20T13:25:36.914Z (about 1 year ago)
- Topics: fastmcp, generative-ai, mcp, mcp-client, mcp-server, rest-api, streamlit
- Language: Python
- Homepage:
- Size: 33.2 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MCP Platform Monorepo
## A modern, extensible platform for building and deploying AI-powered tools with a Streamlit interface and FastMCP backend.
This repository contains two independent projects for building AI-powered tool platforms:
- **classic_api/**: FastAPI backend with a classic Streamlit client.
- **mcp_platform/**: Modern MCP server with an agent-powered Streamlit client.
See each subproject's README for details and setup instructions.
# 🤖 MCP (Model Context Protocol)
[](https://www.python.org/downloads/)
[](https://fastapi.tiangolo.com)
[](https://streamlit.io)
[](https://github.com/psf/black)
[](https://opensource.org/licenses/MIT)
## 🌟 Features
- **🛠️ Modular Tool System**: Easily create and deploy new AI tools
- **🎯 FastAPI Backend**: High-performance, async-ready API endpoints
- **🤖 LangChain Integration**: Powerful agent-based interactions
- **🔍 Built-in Tools**: Ready-to-use tools for common tasks
- **📝 Detailed Documentation**: Comprehensive guides and examples
- **🔒 Secure Design**: Environment-based configuration management
## Quickstart
### classic_api (FastAPI + Streamlit)
1. **Start the backend (FastAPI server):**
```bash
cd classic_api/backend
pip install -r requirements.txt
uvicorn app.fastapi_app:app --reload
```
2. **Start the frontend (Streamlit client):**
```bash
cd ../../frontend
pip install -r requirements.txt
cp .env.example .env # Set your OpenAI key and model
streamlit run streamlit_app.py
```
3. **Open your browser:**
- Visit [http://localhost:8501](http://localhost:8501) for the UI.
- The FastAPI server runs at [http://localhost:8000](http://localhost:8000) by default.
---
### mcp_platform (MCP Server + Streamlit Agent Client)
1. **Start the backend (MCP server):**
```bash
cd mcp_platform/backend
pip install -r requirements.txt
python -m app.mcp_server_app
```
2. **Start the frontend (Streamlit client):**
```bash
cd ../frontend
pip install -r requirements.txt
cp .env.example .env # Set your OpenAI key and model
streamlit run streamlit_app.py
```
3. **Open your browser:**
- Visit [http://localhost:8501](http://localhost:8501) for the chat UI.
- The MCP server runs at [http://localhost:8000/mcp](http://localhost:8000/mcp) by default.
---
### Available Tools
| Tool | Description | Example Usage |
|------|-------------|---------------|
| Add | Add two numbers | "Add 5 and 7" |
| ReverseString | Reverse a string | "Reverse hello world" |
| WordCount | Count words in text | "Count words in this sentence" |
| WikipediaSummary | Get Wikipedia summary | "Summarize Python programming" |
| WebSearch | Search the web | "Search latest AI news" |
| PythonExec | Execute Python code | "Calculate sum([1,2,3])" |
| Greet | Greet a person | "Greet Alice" |