mcp-server-patterns

Topics in the source

• MCP Server Patterns
• When to Use
• How It Works
• Core concepts
• Connecting with stdio
• Remote (Streamable HTTP)
• Examples
• Install and server setup

The Model Context Protocol (MCP) lets AI assistants call tools, read resources, and use prompts from your server. Use this skill when building or maintaining MCP servers. The SDK API evolves; check Context7 (query-docs for "MCP") or the official MCP documentation for current method names and signatures. For the broader routing decision of when a capability should be a rule, a skill, MCP, or a plain CLI/API workflow, see docs/capability-surface-selection.md. Use when: implementing a new MCP server, adding tools or resources, choosing stdio vs HTTP, upgrading the SDK, or debugging MCP registration and transport issues. Tools: Actions the model can invoke (e.g. search, run a command). Register with registerTool() or tool() depending on SDK version. Resources: Read-only data the model can fetch (e.g. file contents, API responses). Register with registerResource() or resource(). Handlers typically receive a uri argument. Prompts: Reusable, parameterised prompt templates the client can surface (e.g. in Claude Desktop). Register with registerPrompt() or equivalent. Transport: stdio for local clients (e.g. Claude Desktop); Streamable HTTP is preferred for remote (Cursor, cloud). Legacy HTT

This is an excerpt. Refer to the complete source and its current requirements.