- Home
- MCP servers
- haos-mcp-ts
haos-mcp-ts
- typescript
0
GitHub Stars
typescript
Language
6 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": {
"stefanwatt-haos-mcp-ts": {
"command": "node",
"args": [
"/absolute/path/to/haos-mcp-ts/dist/index.js"
]
}
}
}You can run the haos-mcp-ts MCP server to expose a Model Context Protocol interface for your Haos-powered applications. It’s built with the MCP framework and lets you create and load tools that process inputs and return results to MCP clients. This server is designed to be run locally during development and to be published for use by Claude Desktop or other MCP clients.
How to use
You interact with the server through an MCP client. Start the server locally, then point your client to the MCP entry point you configured. You can run your own tools by building and loading them into the server, and then you can invoke those tools from the client to perform tasks or data processing.
How to install
Prerequisites: you need Node.js and npm installed on your system.
# Install dependencies
npm install
# Build the project
npm run build
Additional setup and usage notes
The server supports running locally during development and can be published so clients can invoke it via npx. When you run locally, the server loads its tools from the built output. When published, clients can execute the MCP server through the published package.
Building and testing
Make changes to your tools as needed. Then compile and test your server locally.
# Build the project after making changes
npm run build
Configuring the MCP server for Claude Desktop
For local development, you can configure Claude Desktop to load the MCP server. Add a configuration entry that points to the local startup command and the built index file.
Available tools
my_tool
A tool that Describes what your tool does and processes an input message to produce a result.