Financial Analyst

An MCP server for interactive stock analysis using a local LLM with data fetched via yfinance and visualized with matplotlib.

python

1

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "prakharsinghdev-mcp-powered-financial-analyst": {
      "command": "python",
      "args": [
        "server.py"
      ]
    }
  }
}

You run a local MCP server that lets you query and analyze stock market data using a locally hosted language model. It supports interactive conversations, multi‑agent orchestration, and visual results rendered with charts, all accessible through an MCP client or directly in your terminal.

How to use

Connect to the MCP server from your MCP client to start interactive stock analysis. You can ask it to fetch data, perform analyses, and render charts for you. Use natural language prompts such as asking for a stock’s performance over a period, comparing multiple tickers, or reviewing trading volume. The server will fetch data, run analyses, and present results in tables and charts that you can review directly in the MCP interface or in your terminal.

How to install

Prerequisites you need on your system before running the MCP server are Python and a compatible runtime for your chosen run method. You also need a local MCP runner to connect to the server. Follow one of the two run options below to start the server.

Option A: Run via Cursor IDE MCP (stdio) with a local directory-based server

{
  "mcpServers": {
    "financial_analyst_cursor": {
      "command": "uv",
      "args": [
        "--directory",
        "absolute/path/to/project_root",
        "run",
        "server.py"
      ]
    }
  }
}

Option B: Run via Python MCP in a standalone terminal (stdio)

If you prefer not to use Cursor, you can run the server directly in your terminal using Python.

python server.py

Start quickly from scratch with the two options above

Choose one option and follow the respective steps to start the server. After starting, you will be prompted for stock data queries and timeframes. Charts will render in a window or within the MCP client as you request analyses.

Available tools

fetch_stock_data

Retrieves historical stock data using yfinance for the requested symbol and timeframe.

analyze_trends

Performs analytical calculations on the fetched data to identify trends, moving averages, and key statistics.

render_charts

Generates and displays charts using matplotlib to visualize stock performance and volumes.

conversational_analysis

Enables MCP-driven conversational analysis to interpret stock data and present insights.