screener_mcp
0
The Screener.in MCP Server project provides a Model Context Protocol server that allows large language models to interact with Indian stock market data. It offers tools for company data analysis using web scraping methods and focuses on integrating with Claude Desktop for enhanced data interaction.
Screener.in MCP Server
This project offers an MCP server enabling LLMs like Claude to engage with Indian stock market data from Screener.in. It utilizes FastMCP for defining tools and resources to fetch company overviews, financial ratios, and conduct company searches on Screener.in. Users must adhere to Screener.in's terms for automated data use.
Features
- Tools: Fetch company overviews, peer comparisons, and perform company searches.
- Resources: Obtain company overview and peer comparison data.
- Prompts: Generate prompts for company analysis.
Prerequisites
- Python 3.10+
- uv for environment management
- Claude Desktop App for integration
Setup and Installation
- Clone the repository and create a virtual environment.
- Install dependencies using uv.
- Optionally create a .env file for API keys.
Running the Server
- Run locally using defined scripts or FastMCP.
- Integrate with Claude Desktop App by installing and enabling the tool.
Development
- Core data-fetching logic is in screener_utils.py.
- Key files include pyproject.toml for metadata and dependencies.
Future Enhancements
- Add features like caching and improved error handling.
Contributing
Contributions are welcome via issues or pull requests.