Loading
7 permissively-licensed prompts mirrored from mcp-use/mcp-use (MIT). Honest zero stats; every prompt links to its source.
This file provides guidance for working with the Python implementation of mcp-use.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
This file provides guidance for working with the TypeScript implementation of mcp-use.
When improving documentation, follow this iterative process:
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.j
**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP dev
This is the root configuration for Claude Code in the mcp-use monorepo.
A Community Mirror bundle of 7 permissively-licensed prompts from `mcp-use/mcp-use` (MIT).
> Honest mirror. Zero usage stats. Not affiliated with the original authors — each prompt links back to its source file and license.
Clone any prompt into your library, bring your own provider key, and run it on any model. No markup.