Agent skill · software engineering · samhvw8
mcp
Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
Why this skill is useful
Adds executable scripts for building and managing MCP servers, including integration patterns and configuration management that are not widely documented.
What it needs
Requires python, typescript installed locally. About 5k tokens when loaded. Last updated 2025-12-09. 10 stars on the source repository.
What this skill does
MCP: Build & Manage Protocol Servers Build MCP servers that integrate APIs, and execute tools from configured servers. When to Use Building: Create MCP servers (Python/TypeScript), integrate APIs, design agent-centric tools, implement validation/error handling, create evaluations Managing: Discover/execute tools via Gemini CLI, filter tools for tasks, manage multi-server configs Core Concepts MCP = standardized protocol for AI agents to access external tools/data. Components: Tools (executable functions), Resources (read-only data), Prompts (templates) Transports: Stdio (local), HTTP (remote), SSE (real-time) Load: references/protocol-basics.md for full protocol details --- Part 1: Building MCP Servers Build high-quality MCP servers that enable LLMs to accomplish real-world tasks. Development Workflow Phase 1: Research & Planning 1. Study agent-centric design principles (workflows over endpoints) 2. Research target API documentation exhaustively 3. Load framework documentation (Python SDK or TypeScript SDK) 4. Plan tool selection, shared utilities, input/output design, error handling Phase 2: Implementation 1. Set up project structure (single file for Python, full structure for TypeScript) 2. Implement core infrastructure (API clients, error handlers, formatters) 3. Register tools with proper schemas and annotations 4. Follow language-specific best practices Phase 3: Testing & Quality 1. Code quality review (DRY, composability, consistency) 2. Run builds and syntax checks 3. Use quality checklists Phase 4: Evaluation 1. Create 10 complex, realistic evaluation questions 2. Questions must be read-only, independent, and verifiable 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills samhvw8/mcp