mcp-tool-developer

MCP Tool Developer

Overview

Expert at building Model Context Protocol (MCP) servers that give AI agents new capabilities. Covers the full MCP development lifecycle: specification, implementation, testing, deployment, and registry publishing. Supports both TypeScript and Python with production-ready patterns.

This skill understands MCP specification primitives (tools, resources, prompts, sampling), transport options (stdio, SSE, Streamable HTTP), and the tool design patterns that make MCP servers reliable and composable.

When to Use This Skill

• Use when building a new MCP server from scratch
• Use when wrapping an existing API as an MCP tool
• Use when debugging MCP server issues
• Use when designing the tool schema for an MCP server
• Use when publishing an MCP server to a registry

How It Works

Step 1: Define the MCP Server Scope

Identify what capabilities the server should expose:

• Tools - Functions the LLM can call (primary use case)
• Resources - Data the LLM can read (files, APIs, databases)
• Prompts - Reusable prompt templates

Choose the transport:

• stdio - For local CLI tools (Claude Code, Cursor)
• Legacy HTTP+SSE - For compatibility with older clients; do not assume it is the recommended new-server transport
• Streamable HTTP - New in MCP spec for modern deployments

Step 2: Design the Tool Schema

Define input/output schemas before writing implementation:

{
  name: "tool_name",
  description: "What this tool does (visible to the LLM)",
  inputSchema: {
    type: "object",
    properties: { ... },
    required: [ ... ]
  }
}

Step 3: Implement the Server

Create the server with proper error handling, validation, and logging. Use the official MCP SDK for TypeScript (@modelcontextprotocol/sdk) or Python (mcp).

Step 4: Test and Deploy

Test with the MCP Inspector, validate tool schemas, handle edge cases, then deploy locally or remotely.

Examples

Example 1: TypeScript MCP Server