Demo Hello MCP Server Usage Guide¶
Overview¶
This guide shows how to use the Demo Hello MCP Server with different MCP clients and integration methods.
Tool Discovery¶
Available Tools¶
say_hello¶
Description: Generate a personalized greeting message.
PATTERN 1: Uses standard config from config_schema - hello_from: Set via --config hello_from="value" or MCP_HELLO_FROM env var
PATTERN 2: Uses template data that can be overridden - Tool behavior can be modified via --tools__0__greeting_style="formal"
Args: name: Name of the person to greet
Returns: A personalized greeting message
Parameters:
- name
(string) (optional): No description
get_server_info¶
Description: Get information about the demo server.
Shows both standard config and template data that may be overridden.
Returns: Dictionary containing server information
Parameters: - No parameters required
echo_message¶
Description: Echo back a message with server identification.
Demonstrates template data override for tool behavior.
Args: message: Message to echo back
Returns: Echoed message with server identification
Parameters:
- message
(string) (required): No description
demonstrate_overrides¶
Description: Demonstrate the two configuration patterns.
Returns: Examples of both configuration patterns
Parameters: - No parameters required
Usage Examples¶
# Start interactive mode
mcp_platform interactive
# Deploy the template (if not already deployed)
mcpp> deploy demo
# List available tools after deployment
mcpp> tools demo
Then call tools:
import asyncio
from mcp_platform.client import MCPClient
async def use_demo():
client = MCPClient()
# Start the server
deployment = client.start_server("demo", {})
if deployment["success"]:
deployment_id = deployment["deployment_id"]
try:
# Discover available tools
tools = client.list_tools("demo")
print(f"Available tools: {[t['name'] for t in tools]}")
# Call say_hello
result = client.call_tool("demo", "say_hello", {'name': 'example_value'})
print(f"say_hello result: {result}")
# Call get_server_info
result = client.call_tool("demo", "get_server_info", {})
print(f"get_server_info result: {result}")
finally:
# Clean up
client.stop_server(deployment_id)
else:
print("Failed to start server")
# Run the example
asyncio.run(use_demo())
Integration Examples¶
Add this configuration to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Install the MCP extension and add this to your VS Code settings (.vscode/settings.json
):
Configuration¶
For template-specific configuration options, see the main template documentation. Common configuration methods:
Troubleshooting¶
Common Issues¶
-
Template not found: Ensure the template name is correct
-
Connection issues: Check if the server is running
-
Tool discovery fails: Try refreshing the tool cache
Debug Mode¶
Enable debug logging for troubleshooting:
For more help, see the main documentation or open an issue in the repository.