Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Tradersis

FreeNot checked

Tradersis — Model Context Protocol server

GitHubEmbed

About

Tradersis — Model Context Protocol server

README

Introduction

This project is a Model Context Protocol (MCP) server designed to enable LLMs (such as Claude, Cursor, or GPT-based agents) to retrieve, analyze, and visualize stock prices and financial report data. It provides a set of robust tools for quantitative trading research, investment analysis, and financial education.

Usage Scenarios

  • LLM-driven trading analysis: Let LLMs fetch and analyze stock data, financial statements, and technical indicators to generate trading insights.
  • Financial metric calculation: Compute key ratios and metrics from income statements, balance sheets, and cash flow tables.
  • Visualization: Generate price charts, financial metric trends, and highlight trading opportunities.
  • Automated research: Integrate with LLMs to answer questions like "What is the ROE of AAPL?", "Show me the last 6 months of MSFT price data.", or "Plot buy/sell signals for TSLA."

Features

  • Retrieve real-time and historical stock prices (single or multiple tickers)
  • Extract and analyze financial statements (income, balance sheet, cash flow)
  • Calculate key financial and technical metrics (PE, ROE, moving averages, etc.)
  • Visualize price data, metrics, and trading signals
  • LLM-friendly, JSON-serializable outputs

Installation

  1. Clone the repository
    git clone https://github.com/Nan-Shen/mcp-server-tradersis.git
    cd <your-repo-folder>
    
  2. Set up a Python virtual environment
    python3 -m venv .venv
    source .venv/bin/activate
    
  3. Install dependencies
    uv sync
    

How to Run

  1. Configure your LLM client (Claude, Cursor, etc.) to connect to the MCP server and call the available tools.

    Go to Claude settings Select Developer --> Edit Config Add new MCP server. In the JSON File, add

    {"mcpServers": 
         {"tradersis-mcp": {
                "command": "uv",
                "args": [
                "run",
                "--directory",
                "/directory/to/your/mcp",
                "main.py"
            ]
            }
         }
    }  
    

'tradersis-mcp' should now be listed in your Claude tools.

  1. Start talking with your trading assistant!

Quries like:

Compare the stock prices of Nvidia and AMD in the past month.

Comparison Chart Example

How's Tesla stock like in the past 3 months?

Candlestick Chart Example

Plot the trading opportunities of NiSource Inc in the past 3 months.

Trading Opportunity Example

Contact & Contributing

  • Issues and pull requests are welcome!
  • Stars are even more welcome!

from github.com/Nan-Shen/mcp-server-tradersis

Installing Tradersis

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/Nan-Shen/mcp-server-tradersis

FAQ

Is Tradersis MCP free?

Yes, Tradersis MCP is free — one-click install via Unyly at no cost.

Does Tradersis need an API key?

No, Tradersis runs without API keys or environment variables.

Is Tradersis hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Tradersis in Claude Desktop, Claude Code or Cursor?

Open Tradersis on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Tradersis with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All development MCPs