new-mcp-tool— agent skill

Create a new MCP tool following project conventions. Use $ARGUMENTS for the tool name and description.

Steps

1. Create tool class in the appropriate tools directory

• Static class with [McpServerToolType] attribute
• Static method with [McpServerTool(Name = "snake_case_name")] attribute
• Add [Description("...")] on EVERY parameter
• Use flat parameters (no complex objects)
• Nullable optional service injection for wallet services
• Include IsConfigured check — return error result if required service not configured

1. Add models to the appropriate models file if needed

• Request/response records

1. Add service interface method in the service interface if the tool needs business logic beyond direct API calls

1. Implement service method in the implementation class

1. Update DI registration in Program.cs if new services are needed

1. Write tests following existing test patterns

Patterns to Follow

[McpServerToolType]
public static class MyNewTool
{
    [McpServerTool(Name = "my_new_tool")]
    [Description("What this tool does")]
    public static async Task<string> Execute(
        [Description("Parameter description")] string requiredParam,
        [Description("Optional parameter")] string? optionalParam = null,
        IMyService? myService = null)
    {
        if (myService is null || !myService.IsConfigured)
            return "Error: MyService is not configured. Set MY_ENV_VAR environment variable.";

        // Implementation
        return JsonSerializer.Serialize(result, new JsonSerializerOptions { WriteIndented = true });
    }
}

Key Conventions

• Tool name: snake_case (e.g., get_btc_price, check_wallet_balance)
• Class name: PascalCase + "Tool" suffix
• Return JSON-serialized results for structured data
• Use [Description] on every parameter — MCP clients use these for documentation
• Wallet priority: LND > NWC > Strike > OpenNode
• L402 requires preimage — only works with LND, Strike, CoinOS NWC, CLINK NWC, Alby Hub NWC

Free vs Paid

When you add a tool, update the inventory guard tests — they are the single source of truth for the advertised tool count, and they fail until the code and the declared lists match:

• FREE_TOOLS in python/lightning-enable-mcp/tests/test_server.py and FreeTools in dotnet/tests/LightningEnable.Mcp.Tests/ToolInventoryTests.cs — tools that work with just a wallet (no license).
• API_KEY_TOOLS / ApiKeyTools in the same files — tools that require an Agentic Commerce subscription + LIGHTNING_ENABLE_API_KEY (e.g. the producer tools create_l402_challenge, verify_l402_payment). Add license-check logic in the tool itself if it should be paid.

Public docs no longer hard-code the count (except the MCP Complete Guide's self-counting table), so there is nothing else to bump.

Suggested follow-up: /mcp-publish-prep when ready to publish