investbuddy
mcp server for investbuddy
claude mcp add --transport stdio danielrz-investbuddy-mcp-server node /absolute/path/to/investbuddy-mcp/build/index.js \ --env INVESTBUDDY_API_KEY="your_api_key_here"
How to use
InvestBuddy MCP Server connects Claude Desktop to the InvestBuddy institutional-grade LSTM quantitative trading engine. It exposes a focused set of tools that return portfolio-level insights and market context derived from the underlying LSTM model, including current month top stock selections, defensive posture checks, and market sentiment signals across a 50-stock universe. This allows Claude to provide data-driven assessments and recommendations without relying on generic financial heuristics. To use it, install the MCP server as part of your Claude Desktop integration and configure it in your mcpServers section so Claude can invoke the InvestBuddy tools through the MCP channel. The key tools available are get_portfolio_recommendations, check_defensive_posture, and analyze_market_context, enabling you to query stock picks, defensive shifts to cash when risk is high, and sentiment across the monitored universe, respectively.
How to install
Prerequisites:
- Node.js v18 or higher
- Claude Desktop installed
- An InvestBuddy API Key
Step 1: Clone the repository and install dependencies
git clone https://github.com/yourusername/investbuddy-mcp.git
cd investbuddy-mcp
npm install
npm run build
Step 2: Obtain and set up your API key
- Acquire an InvestBuddy API Key from investbuddy.ai
- Store the key securely; you will reference it in the MCP config env var
Step 3: Configure Claude Desktop to use the MCP server
- Open Claude Desktop config (Mac: ~/Library/Application Support/Claude/claude_desktop_config.json; Windows: %APPDATA%\Claude\claude_desktop_config.json)
- Add the InvestBuddy MCP server to mcpServers (see example in the README):
{
"mcpServers": {
"investbuddy": {
"command": "node",
"args": ["/absolute/path/to/investbuddy-mcp/build/index.js"],
"env": {
"INVESTBUDDY_API_KEY": "your_api_key_here"
}
}
}
}
- Restart Claude Desktop
Step 4: Test the integration
- In Claude, ask for a portfolio analysis or market context and verify responses align with the InvestBuddy outputs (Top 5 picks, defensive posture, market sentiment).
Additional notes
Tips and caveats:
- Ensure the INVESTBUDDY_API_KEY is kept secret and not checked into version control.
- The MCP server serves real-time signals based on the LSTM model; backtesting results in the README reflect historical performance and are not guarantees of future results.
- If Claude cannot reach the MCP server, verify that Node is installed, the path to build/index.js is correct, and the environment variable is set.
- You can adjust the available tools or add more environment-based configurations as needed in the future; keep the config aligned with Claude's expectations for mcpServers entries.
- When upgrading, rebuild the project and revalidate the path in the Claude Desktop config.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.