Financial

Financial MCP Server

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 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": {
    "osamadev-financial_mcp_server": {
      "command": "mcp",
      "args": [
        "run",
        "server.py"
      ],
      "env": {
        "SERPAPI_API_KEY": "YOUR_SERPAPI_KEY",
        "TELEGRAM_CHAT_ID": "YOUR_TELEGRAM_CHAT_ID",
        "TELEGRAM_BOT_TOKEN": "YOUR_TELEGRAM_BOT_TOKEN"
      }
    }
  }
}

You are about to run a dedicated MCP server that provides real-time market insights, portfolio tracking, and contextual financial analysis. This server exposes practical tools for monitoring stocks, building market-aware prompts, and sending automated alerts, all accessible from MCP-compatible clients to help you act on financial information quickly.

How to use

Connect with a Claude Desktop or other MCP client and enable the available tools from your Financial MCP Server. Use the financial_context tool to analyze a query, extract tickers, fetch relevant news, and receive a market-aware prompt. Retrieve a live market_summary to see indices, movers, and headlines. Manage your portfolio with add_stock, remove_stock, and get_portfolio. Set up portfolio_alerts to receive Telegram notifications for price thresholds and trading opportunities. Use the contextual summarization features to get sentiment-tagged news summaries and generate actionable prompts for downstream tasks.

How to install

Prerequisites: Python 3.7+, a MCP-compatible client, Telegram bot credentials, and an internet connection.

Step-by-step commands to set up and run the server locally.

Additional setup and configuration

Environment variables control alerting and data access. You will configure Telegram and news fetch keys to enable full functionality.

Use the provided alert configuration files to organize sectors, tickers, and thresholds. The system supports persistent portfolios, live market data, and automated Telegram alerts.

Troubleshooting & logs

All logs are written to a log file named financial_mcp.log in the project root. If you encounter issues, verify environment variables, configuration files, and network access to data sources.

Available tools

financial_context

Extracts tickers and keywords from a user query, fetches and summarizes relevant news, and returns a structured context and prompt for downstream analysis.

market_summary

Returns a live summary of global markets, including indices, top movers, and news headlines.

get_portfolio

Retrieves the current list of tracked stocks in the user's portfolio.

add_stock

Add a stock to the portfolio and validate its presence in the portfolio cache.

remove_stock

Remove a stock from the portfolio and invalidate cache as needed.

portfolio_alerts

Returns all triggered alerts for the portfolio, or for a specific ticker if provided.

check_stock_alerts

Returns alerts for a specific stock with detailed error handling.

single_stock_alert

Returns alerts for a single stock with error handling and context.

News Summarizer

Generates sentiment-tagged summaries of financial news articles using a local LLM.

Prompt Builder

Constructs market-aware prompts for downstream LLMs or assistants.