- Home
- MCP servers
- Brokerage
Brokerage
- typescript
0
GitHub Stars
typescript
Language
5 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": {
"raghavc16-brokerage-mcp": {
"command": "npx",
"args": [
"-y",
"Brokerage-MCP"
]
}
}
}This MCP server provides a Model Context Protocol interface for brokerage tooling, enabling you to run and manage tools locally or from a CLI client. It is built with the MCP framework to expose tools as reusable endpoints you can invoke from your clients or desktop integration.
How to use
You can run brokerage tools from a local client or through a Claude Desktop integration. Start the server locally after building, then connect your client to the MCP runtime using the provided stdio configurations. When connected, you can execute tools, pass inputs, and receive structured results from the server.
How to install
Prerequisites: you need Node.js and npm installed on your machine.
Install dependencies for the project.
npm install
Build the project to produce executable artifacts.
npm run build
Run the server locally after building. The server entry point is available under the dist folder.
node dist/index.js
Additional notes
Two ready-to-use runtime configurations are provided for Claude Desktop to connect to the server:
- Local development uses a direct node command pointing to the built entry file.
- After publishing, you can connect via npx to run the published MCP package from the CLI.
Local development configuration example for Claude Desktop: use an absolute path to the built entry file in dist.
After publishing, Claude Desktop can start the MCP server via npx with the package name.
Tips for development and testing
Add new tools to extend capabilities by using the provided tooling workflow. Each tool implements its own input schema and execution logic, enabling structured and repeatable tool invocations.
Build and test locally to ensure tools load correctly on startup, and verify client interactions against the MCP runtime.
Available tools
my_tool
Describes what your tool does