mcpField
H
Hello MCP Server

Hello MCP Server

Local
github.com/cjavierDeveloper Tools0Updated 82w ago
Repository

About Hello MCP Server

Hello MCP Server is a TypeScript MCP server built with the Forge task runner, for developers connecting Claude and other compatible assistants to external services and data. Forge tasks are automatically exposed as MCP tools.

Key features

  1. 01Forge task runner integration
  2. 02Tasks exposed as MCP tools
  3. 03Run tasks directly with Forge CLI
  4. 04MCP Inspector testing support

Use cases

  1. 01Expose a custom Forge task to an MCP assistant
  2. 02Run the stock price task with a ticker
  3. 03Test server tools and responses in MCP Inspector

MCP support

The server exposes tasks registered with its Forge runner as tools for MCP clients. It can be configured for Claude Desktop and tested with MCP Inspector.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "McpServerBasic": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/inspector

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/inspector

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Hello MCP Server

This is a Model Context Protocol (MCP) server implementation that enables AI assistants to interact with external services and data sources. The server is designed to work with Claude and other MCP-compatible AI assistants.

Prerequisites

  • Node.js (v18 or higher)
  • pnpm package manager
  • force CLI, install with pnpm i -g @forgehive/forge-cli

Installation

Clone the repository and install dependencies:

git clone <repository-url>
cd hello-mcp-server
pnpm install

Build

Build the project with:

pnpm run build

This will compile TypeScript into JavaScript in the dist directory.

Running Tasks Directly

You can run individual tasks directly using the Forge runner:

# Run the stock price task with a ticker parameter
forge task:run stock:price --ticker AAPL

Adding to Claude Desktop

To use the server with Claude Desktop:

  1. Build the project with pnpm run build
  2. Modify the Claude Desktop configuration file:

With nano: ~/Library/Application Support/Claude/claude_desktop_config.json

{
    "mcpServers": {
        "hello-mcp-server": {
            "command": "node",
            "args": [
                "ABSOLUTE_PATH_TO_PROJECT/hello-mcp-server/dist/index.js"
            ]
        }
    }
}

Replace ABSOLUTE_PATH_TO_PROJECT with the actual absolute path to your project directory.

Using MCP Inspector

For debugging and testing your MCP server, you can use the MCP Inspector tool:

npx @modelcontextprotocol/inspector ABSOLUTE_PATH_TO_PROJECT/hello-mcp-server/dist/index.js

The inspector provides a web interface to test your server's tools and see their responses.

Development

To add new tasks:

  1. Create a new task using the Forge CLI:

    forge task:create MODULE:TASK_NAME

    This will generate a task template file in src/tasks/MODULE/TASK_NAME.ts.

  2. Implement your task in the generated file using the Forge Task API.

  3. Register the task in the runner (src/runner.ts):

    import { yourTask } from './tasks/module/your-task';

// Add your task to the runner
runner.load('your_task_name', yourTask);

  4. Build the project with pnpm run build

The server will automatically register all tasks from the runner as MCP tools without needing to manually add them to the src/index.ts file.

Additional Resources

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.