hello_world_dart_mcp_server
A simple Hello World MCP server written in Dart that demonstrates basic MCP server implementation with two example tools: say_hello and get_server_info.
README
Hello World MCP Server
A simple Hello World MCP (Model Context Protocol) server written in Dart that demonstrates basic MCP server implementation with two example tools.
Overview
This MCP server provides a minimal example of how to implement an MCP server in Dart. It includes two basic tools:
say_hello: Greets a person with an optional custom messageget_server_info: Returns information about the MCP server
Features
- JSON-RPC 2.0 protocol implementation
- Stdio-based communication
- Cross-platform support (Windows, Linux, macOS)
- Native binary compilation
- Simple tool demonstration
Requirements
- Dart SDK 3.0.0 or later
- Compatible MCP client
Installation
Option 1: Using Dart Runtime (Development)
-
Clone this repository:
git clone <repository-url> cd hello-world-server -
Install dependencies:
dart pub get -
Run the server:
dart run bin/hello_world_mcp_server.dart
Option 2: Using Pre-built Binaries (Production)
Download the appropriate binary for your platform from the Releases page:
- Windows:
hello_world_mcp_server-windows-amd64.exeorhello_world_mcp_server-windows-arm64.exe - Linux:
hello_world_mcp_server-linux-amd64orhello_world_mcp_server-linux-arm64 - macOS:
hello_world_mcp_server-macos-amd64orhello_world_mcp_server-macos-arm64
Linux/macOS Setup:
# Make the binary executable
chmod +x hello_world_mcp_server-linux-amd64
# Run the server
./hello_world_mcp_server-linux-amd64
Windows Setup:
# Run directly
hello_world_mcp_server-windows-amd64.exe
Option 3: Build from Source
# Install dependencies
dart pub get
# Compile to native executable
dart compile exe bin/hello_world_mcp_server.dart -o hello_world_mcp_server
# Run the compiled binary
./hello_world_mcp_server # Linux/macOS
hello_world_mcp_server.exe # Windows
Usage
Running the MCP Server
The MCP server communicates via stdin/stdout using the JSON-RPC 2.0 protocol. It's designed to be used with MCP-compatible clients.
Using Native Dart Runner
dart run bin/hello_world_mcp_server.dart
Using Compiled Binary
# Linux/macOS
./hello_world_mcp_server-linux-amd64
# Windows
hello_world_mcp_server-windows-amd64.exe
MCP Client Configuration
To use this server with an MCP client, configure it as a stdio-based server:
Example Configuration (MCP Client)
{
"mcpServers": {
"hello-world": {
"command": "dart",
"args": ["run", "/path/to/hello-world-server/bin/hello_world_mcp_server.dart"]
}
}
}
Using Binary in MCP Client
{
"mcpServers": {
"hello-world": {
"command": "/path/to/hello_world_mcp_server-linux-amd64"
}
}
}
Manual Testing
You can test the server manually by sending JSON-RPC messages:
# Initialize the server
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' | dart run bin/hello_world_mcp_server.dart
# List available tools
echo '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' | dart run bin/hello_world_mcp_server.dart
# Call the say_hello tool
echo '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"say_hello","arguments":{"name":"World","message":"Greetings"}}}' | dart run bin/hello_world_mcp_server.dart
# Get server information
echo '{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"get_server_info","arguments":{}}}' | dart run bin/hello_world_mcp_server.dart
Available Tools
say_hello
Greets a person with an optional custom message.
Parameters:
name(required, string): The name of the person to greetmessage(optional, string): Custom message (defaults to "Hello")
Example:
{
"name": "say_hello",
"arguments": {
"name": "Alice",
"message": "Good morning"
}
}
Response:
Good morning, Alice! š
get_server_info
Returns information about this MCP server.
Parameters: None
Example:
{
"name": "get_server_info",
"arguments": {}
}
Response:
Hello World MCP Server Information:
- Name: hello-world-server
- Version: 1.0.0
- Language: Dart
- Protocol Version: 2024-11-05
- Available Tools: say_hello, get_server_info
This is a simple demonstration MCP server that shows how to implement basic tools using Dart.
Development
Project Structure
hello-world-server/
āāā bin/
ā āāā hello_world_mcp_server.dart # Main server implementation
āāā dagger/
ā āāā build_script.py # Dagger build script for multi-platform builds
āāā artifacts/ # Build output directory (created by Dagger)
āāā BUILD.md # Detailed build instructions
āāā LICENSE # MIT License
āāā pubspec.yaml # Dart project configuration
āāā pyproject.toml # Python project config for Dagger builds
āāā README.md # This file
āāā .gitignore # Git ignore rules
Running in Development
# Install dependencies
dart pub get
# Run the server
dart run bin/hello_world_mcp_server.dart
# Run with debugging output
dart run bin/hello_world_mcp_server.dart 2>debug.log
Building
Option 1: Using Dagger (Recommended)
This project uses Dagger for reproducible, containerized builds across all platforms.
Note for Windows developers, Python is used for the dagger builds, but that piece is best done in 'nix.
Prerequisites:
- Python 3.11+
- Docker (for Dagger)
Build all platforms:
# Install Python dependencies
pip install -r requirements.txt
# Run the Dagger build script
python build_script.py
This will build binaries for:
- Windows (AMD64, ARM64)
- Linux (AMD64, ARM64)
- macOS/Darwin (AMD64, ARM64)
All binaries will be saved to the artifacts/ directory.
Using pyproject.toml:
# Install in development mode
pip install -e .
# Run the build command
build-binaries
Option 2: Manual Build
See BUILD.md for comprehensive build instructions, including:
- Manual compilation
- Cross-platform building
- Release process
Protocol Details
This server implements the MCP (Model Context Protocol) specification:
- Protocol Version: 2024-11-05
- Transport: stdio (stdin/stdout)
- Message Format: JSON-RPC 2.0
- Capabilities: Tools
Supported Methods
initialize- Initialize the MCP sessionnotifications/initialized- Acknowledge initializationtools/list- List available toolstools/call- Execute a tool
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test thoroughly
- Submit a pull request
Please ensure your changes:
- Follow Dart coding conventions
- Include appropriate tests
- Don't break existing functionality
- Update documentation as needed
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
For issues, questions, or contributions, please use the GitHub repository's issue tracker.
Related
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.