Loading repository data…
faryasir07 / repository
An Model Context Protocol (MCP) server that enables LLMs to perform live financial analysis and data visualization on your local machine. This project bridges the gap between high-speed cloud intelligence (Groq / OpenAI) and local Python execution.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A powerful Model Context Protocol (MCP) server that enables LLMs to perform live financial analysis and data visualization on your local machine. This project bridges the gap between high-speed cloud intelligence (Groq / OpenAI) and local Python execution.
1)Dual-Access Architecture:Runs seamlessly with LangGraph (local client) and the ChatGPT Desktop app (remote client via ngrok).
2)Agentic Code Execution: The agent doesn't just "talk" about stocks; it writes, saves, and executes real Python code using yfinance and matplotlib.
3)Standardized Protocol: Built on the FastMCP framework for reliable, typed tool-calling.
4)Zero-UI Visualization: Automatically generates and saves visual charts (plot.png) directly to your workspace.
1)The system operates using a Server-Client model:
2)The Server (mcp_server.py): A FastMCP instance that exposes a save_and_run_finance_code tool. It listens on port 8000 using the SSE (Server-Sent Events) transport.
3)The Bridge (ngrok): Tunnels the local SSE port to a public URL so ChatGPT Desktop can safely reach your local tools.
4)The Client (LangGraph): A local stateful agent that uses Groq (gpt-oss-120b) to reason and decide when to trigger the financial tools.
pip install -r requirements.txt
Create a .env file in the root directory:
GROQ_API_KEY=your_groq_api_key_here
Start the server in SSE mode to support both local and remote connections:
python mcp_server.py
To use this as a "Custom Connector" in ChatGPT:
1)Start an ngrok tunnel: ngrok http 8000
2)Copy the http URL.
In ChatGPT Desktop: Settings > Apps > Create App.
URL: https://your-ngrok-url.app/sse (Important: add /sse at the end).
Once the server is live, you can ask your agent:
"Plot the price of Nvidia (NVDA) vs AMD (AMD) over the last 6 months and calculate the moving average."
The agent will:
->Generate a Python script (analytics.py).
Selected from shared topics, language and repository description—not editorial ratings.
rcontesti /
This project provides an Interactive Brokers (IB) API interface using the Model Context Protocol (MCP).
79/100 healthhannesrudolph /
An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.
65/100 health->Fetch data via yfinance.
->Execute the script locally.
->Produce a file named plot.png in your folder.
This server allows the LLM to execute Python code on your machine via subprocess. While powerful, always run this in a trusted environment. For production use, consider wrapping the execution in a Docker container to isolate the script from your main OS.
mcp_server.py: The FastMCP server definition and tool logic.
mcp_client.py: The LangGraph orchestration script.
analytics.py: (Generated) The latest script created by the AI.
plot.png: (Generated) The visual output of the analysis.
requirements.txt:Required libraries to install.
jianzhichun /
An MCP (Model Context Protocol) server designed to interact with an already running Abaqus/CAE Graphical User Interface (GUI). It allows for the execution of Python scripts within the Abaqus environment and retrieval of messages from the Abaqus message log/area, all through MCP tools.
78/100 healthHaohao-end /
A modular Python framework implementing the Model Context Protocol (MCP). It features a standardized client-server architecture over StdIO, integrating LLMs with external tools, real-time weather data fetching, and an advanced RAG (Retrieval-Augmented Generation) system.
71/100 healthIRedDragonICY /
An AI-powered Virtual YouTuber (Vtuber) utilizing Google's Gemini language model to create engaging, personalized, and context-aware interactions. This project explores the potential of AI in human-computer interaction and virtual content creation.
67/100 healthnim444 /
MCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.
74/100 health