fugle-marketdata
MCP server from fugle-dev/fugle-marketdata-mcp-server
claude mcp add fugle-dev-fugle-marketdata-mcp-server
How to use
This MCP server enables real-time and historical stock market data queries through the Fugle MarketData MCP. It uses the Fugle MarketData SDK and exposes an MCP interface that lets clients request current prices and historical price data. To get started, obtain an API key from Fugle MarketData and configure the server with your key in the API_KEY environment variable. The server is typically run via npx using the provided release tarball in the configuration, which keeps it easy to deploy without building from source. Once running, clients can connect using the MCP protocol and issue prompts like asking for the latest price of a stock or historical price data for a range of dates.
How to install
Prerequisites:
- Node.js and npm installed
- An API_KEY from Fugle MarketData
- Access to run npm/pnpm/yarn commands if needed
Step-by-step:
- Install Node.js from the official site if you don’t have it
- Ensure npm is available (npm comes with Node.js)
- Start using the MCP server with the provided npx command in your configuration. For example, to preload the server you would run the command that points to the tarball in your environment, which downloads and runs the MCP server in-place:
npx -y https://github.com/fugle-dev/fugle-marketdata-mcp-server/releases/download/v0.0.1/fugle-marketdata-mcp-server-0.0.1.tgz
- Set the required environment variable for API access:
export API_KEY=<Your Fugle MarketData API Key>
- Integrate with Claude Desktop or your MCP client by updating the mcp config as shown in the example configuration.
Additional notes
Tips and common notes:
- Ensure the API_KEY environment variable is secure and not logged or shared.
- The mcp configuration uses an npx-based run from a tarball release; ensure network access to download the tarball.
- If you update the release version, adjust the tarball URL accordingly in your config.
- This server supports real-time quotes and historical data queries; verify the specific MCP prompts you feed align with the supported intents.
- If you encounter connectivity issues, check that Node.js and npm are properly installed and that the environment can access the internet to fetch the tarball.
- For debugging, run the MCP server in verbose mode if supported by the package to capture request/response traces.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud