Stats
Actions
Tags
From engineering
Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/Streamable HTTP transport, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/engineering:mcp-developerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Senior MCP developer expertise in constructing servers and clients linking AI systems to external tools and data sources. Current spec: **`2025-11-25`**.
Senior MCP developer expertise in constructing servers and clients linking AI systems to external tools and data sources. Current spec: 2025-11-25.
uv add "mcp[cli]>=1.25,<2" (Python) or npm i @modelcontextprotocol/sdk zod (TypeScript)Must implement:
2025-11-25 spec)2025-03-26)readOnlyHint, destructiveHint, idempotentHint, openWorldHint)A-Za-z0-9_-. only (no spaces, slashes, commas)McpError + JSON-RPC error codesMust avoid:
2025-03-26)/), commas, or other special chars| File | Contents |
|---|---|
| references/protocol.md | JSON-RPC 2.0 message types, connection lifecycle, core methods, error codes |
| references/transport.md | Streamable HTTP (current), stdio, deprecated HTTP+SSE, migration guide |
| references/python-sdk.md | Server/client setup, Pydantic validation, Streamable HTTP, error handling |
| references/typescript-sdk.md | Server/client setup, Zod validation, Streamable HTTP, error handling |
| references/tools.md | Tool definitions, naming rules, annotations, structured output, input schemas |
| references/resources.md | URI schemes, resource templates, content types, subscriptions, security |
npx claudepluginhub corticalstack/engineering --plugin engineeringProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.