mcp-developer

Implement MCP servers and clients with JSON-RPC 2.0 protocol compliance.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/pgm1980/stryker-netx --skill mcp-developer-pgm1980
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-developer
Source: https://github.com/pgm1980/stryker-netx/tree/main/.claude/skills/tech-dept/mcp-developer
Command: npx skills add https://github.com/pgm1980/stryker-netx --skill mcp-developer-pgm1980

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

MCP developers need a reliable way to connect AI systems to external tools and data sources without breaking JSON-RPC protocol expectations or producing invalid tool inputs and responses.

Core Features & Use Cases

  • End-to-end MCP server/client workflow: design tools, resources, and prompts; implement handlers; run and iterate to correctness.
  • Transport setup across environments: configure stdio, HTTP, or SSE transports and ensure the protocol lifecycle works in practice.
  • Schema-first validation: validate tool inputs using Zod (TypeScript) or Pydantic (Python) so invalid arguments fail predictably and return well-formed JSON-RPC errors.
  • Protocol compliance testing loop: use the MCP inspector to confirm tool/resource visibility and verify request/response shapes, then fix schema or handler serialization issues based on failures.
  • Reference-led implementation: follow targeted guidance for protocol, TypeScript SDK, Python SDK, tools, and resources.

Quick Start

Use the MCP inspector to verify that your newly implemented tools and resource handlers appear correctly and that invalid inputs return well-formed JSON-RPC 2.0 error responses.

Frequently Asked Questions about mcp-developer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate tool inputs in an MCP server using Zod or Pydantic?

To validate MCP tool inputs, define schemas using Zod for TypeScript or Pydantic for Python. This ensures invalid arguments fail predictably and return well-formed JSON-RPC 2.0 error responses instead of breaking server execution.

What is the best way to debug JSON-RPC 2.0 lifecycle issues in Model Context Protocol servers?

The best way to debug JSON-RPC 2.0 lifecycle issues in Model Context Protocol servers is using the MCP inspector to confirm tool visibility, verify request/response shapes, and identify handler serialization failures.

Can I configure stdio, HTTP, and SSE transports for Model Context Protocol servers?

Yes, you can configure stdio, HTTP, or SSE transports for Model Context Protocol servers. This involves setting up the transport layers and ensuring the protocol lifecycle works correctly in practice across your chosen environment.

How do I implement authenticated execution paths for MCP tools?

To implement authenticated execution paths for MCP tools, design your server handlers to enforce authorization checks before processing requests. This ensures only validated requests produce structured JSON content responses.

Why do my MCP tool handlers return invalid JSON-RPC responses?

MCP tool handlers return invalid JSON-RPC responses when schemas or handler serialization are configured incorrectly. Use the MCP inspector to verify request and response shapes, then fix the serialization issues based on the failures.