mcp-builder
MCP Server Development Guide
Overview
Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
Process
🚀 High-Level Workflow
Creating a high-quality MCP server involves four main phases:
Phase 1: Deep Research and Planning
1.1 Understand Modern MCP Design
More from prulloac/agent-skills
github-pull-request
Create pull requests on GitHub using GitHub MCP, GitHub CLI (gh), or the GitHub REST API. Use this skill when the user wants to submit changes as a pull request, following repository standards and templates.
20semver-changelog
Automate the creation and updating of a CHANGELOG.md file based on Semantic Versioning (SemVer) and "Keep a Changelog" principles. Use this skill when you need to summarize changes between the current HEAD and the latest git tag, or when initializing a new changelog for a project.
20custom-agent-creator
Skill to create custom agents for VS Code Copilot or OpenCode, helping users configure and generate agent files with proper formatting and configurations. Use when users want to create specialized AI assistants for VS Code Copilot (.agent.md files) or OpenCode (JSON/markdown agent configs) with specific tools, prompts, models, and behaviors. If the user is not specific about the target platform, ask them to specify Copilot or OpenCode.
20markdown-crossref-validator
Validate cross-references in markdown documents, ensuring links and references point to existing sections, headings, or files.
14vscode-extension-builder
Guide for creating Visual Studio Code extensions/plugins. Use when users want to build VS Code extensions, add functionality to VS Code, create language support, add themes, build webviews, implement debuggers, or any VS Code plugin development task. Helps navigate VS Code Extension API documentation and provides guidance on extension capabilities, project setup, and best practices.
14system-prompt-validator
Validate agent system prompts (such as agents.md) for being objective-driven, clear, readable, free of duplicated intentions, without missing or broken links, and ensuring required sections like general agentic guidelines, code review, and code generation are present. Use when validating or reviewing agent prompt files.
13