frontend verification and debugging.
mcp-builder;anthropics/skills;main/skills/mcp-builder;A guide for building high-quality MCPservers to enable LLMs to interact with external services via well-designed tools.
canvas-design
Skillz
> Self-extending MCPserver — let your AI create and execute custom tools at runtime. No server restarts needed.
## About
Skillz is a Rust-based MCP (Model Context Protocol) server
Skillz - Self-Extending MCPServer
## Overview
Skillz is an MCP (Model Context Protocol) server that enables AI agents to build and execute custom tools at runtime. Let your AI create
methodology, task set, baseline, or raw data, and attributes the gain to third-party MCPservers rather than to itself.
- Strongest measured wins, each rerunnable offline:
- Unnecessary edits to already
overwriting the SDK server instance. Built-in and late programmatic filters, tool/prompt/resource inventories, schemas, transports and persistence behavior remain unchanged; this release does not claim MCP `2026-07-28` support
plain Java.
## Overview
This SDK is a lightweight, annotation-based framework for building MCPservers in plain Java. Define MCP Resources / Prompts / Tools / Completions with ordinary Java methods
MCP is the standard choice for Spring applications. This SDK is for lightweight Java MCPservers where a Spring runtime is unnecessary or undesirable.
## Positioning
| Project | Best fit | Role |
|---------|----------|------|
| Official
cubrid-mcp-server
> A Model Context Protocol server that lets LLM clients inspect CUBRID schemas and run read-only queries through pycubrid.
## Key facts
- Requires Python 3.10 or newer
GitHub to MCP
> Convert any GitHub repository into an MCPserver for AI assistants
## Summary
GitHub to MCP is a tool that automatically generates Model Context Protocol (MCP) servers from
Inspection (local MITM HTTPS proxy), a socket-based BrightScript Debugger, Action Scripts automation, an MCPserver for AI agents, and a `rds` terminal CLI. Works on the local network, over
Remove stale messages with `/context drop` without starting a new session.
- **Dynamic MCP loading**: MCPservers stay pending at startup. Tool schemas only enter context when explicitly needed.
- **Multi-provider
lyra-tool-discovery
> AI powered automation toolkit which acts as an agent that discovers MCPservers for you. Point it at GitHub/npm/configure your own discovery, let GPT or Claude analyze
lyra-tool-discovery
> AI powered automation toolkit which acts as an agent that discovers MCPservers for you. Point it at GitHub/npm/configure your own discovery, let GPT or Claude analyze