Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Design high-quality MCP servers around workflows, narrow schemas, context-aware outputs, and actionable errors. Use when building or reviewing MCP tools for real agent tasks.
Baut aus einer API-Dokumentation einen funktionierenden MCP-Server in Python oder TypeScript, damit Claude direkt mit einem externen Dienst arbeiten kann (CRM, Buchhaltung, eigenes System). Inklusive Installation in Claude Desktop oder Claude Code. Nutze diesen Skill, wenn der User sagt "bau mir einen MCP-Server", "verbinde Claude mit [Tool]", "MCP für [API]", "eigenen Konnektor bauen", "build an MCP server", "create MCP integration", "connect Claude to my API", "custom connector".
Use when working on the md-vision MCP server — adding or changing tools, wiring the stdio transport, validating with the MCP Inspector, or debugging tool schemas and multimodal responses. Scoped to this repo only (local stdio, TypeScript, tools-only).
Use when the user wants to expose their tools, APIs, or data to an AI agent via the Model Context Protocol — building a new MCP server (tools/resources/prompts), choosing stdio vs HTTP transport, writing tool JSON Schemas, or connecting a built server to Hermes or another MCP client.
Guide for configuring and using the GitHub MCP server within Agentic Workflows, including toolset selection, authentication modes, and available GitHub API tools. You MUST load this skill when configuring the GitHub MCP server or its toolsets.
Build MCP servers with Node/TypeScript SDK: tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP servers with Node/TypeScript SDK: tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP (Model Context Protocol) servers with Effect using McpServer, McpSchema, Tool, and Toolkit. Use this skill when implementing MCP servers that expose tools, resources, and prompts to LLM clients via stdio or HTTP transports.
Model Context Protocol (MCP) server implementation specialist for Claude Desktop integration. Handles TypeScript/Node.js server scaffolding, endpoint creation, telemetry setup, npx distribution, and comprehensive documentation. Follows MCP specification and best practices for production-grade server deployment.
Scaffold and govern an MCP server as a bounded tool seam. Defines which tools the agent may call, enforces the principle that agents call tools and tools call infrastructure. Trigger when adding or reviewing an MCP server in an agent system.
Builds production Model Context Protocol (MCP) servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk). Use when the user asks to create an MCP server, expose tools/resources to Cursor or Claude, or integrate APIs via MCP.
Design and scaffold an MCP server for webhook.co. Use when adding or extending the MCP surface (apps/mcp), exposing a capability as MCP tools, or deciding how an MCP server should be deployed and structured.
Generate a complete Model Context Protocol server project in Java using the official MCP Java SDK with reactive streams and optional Spring Boot integration.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.