MCP and tools
MCP servers, agent skills and coding agents: what each can read, write or reach, how to scope them, and how to keep a mistake contained.
Threads in MCP and tools
- ✓
Is GitHub Copilot free, and what does the free plan include?
GitHub Copilot has a free tier. Copilot Free costs $0 and includes 2,000 code completions a month, a monthly allowance of GitHub AI Credits for chat, agent...
0replies - ✓
How do you install and set up Claude Code?
To install Claude Code, run Anthropic's native installer in a terminal (curl -fsSL https://claude.ai/install.sh bash on macOS, Linux and WSL), then open your...
2replies - ✓
What are the parts of an MCP setup: host, client and server?
An MCP setup has three parts: the host, the AI app you use (Claude Code, VS Code); one client per server, created by the host to hold that connection; and the...
2replies - ✓
What is Cursor, and how is it different from VS Code with Copilot?
Cursor is a code editor with a built-in AI coding agent, made by Anysphere and based on the VS Code codebase. VS Code with Copilot is Microsoft's editor plus...
2replies - ✓
How do you build a simple AI agent that can edit code?
To build a simple AI agent that can edit code, give a model an editing tool through its provider's API, run every tool call it asks for in your own code, send...
1reply - ✓
How do you use GitHub Copilot for the first time?
To use GitHub Copilot for the first time, open VS Code, select the Copilot icon in the Status Bar, choose Use AI Features and sign in with GitHub. Without a...
1reply - ✓
What is an AI agent, and how is a coding agent different from a chatbot?
An AI agent is a language model that decides its own next steps and uses tools in a loop until a task is done. A coding agent is one whose tools read files...
2replies - ✓
What is Ollama, and is it safe to run models locally?
Ollama is a free, MIT-licensed program that downloads open-weight language models and runs them on your own computer, with a local API on port 11434. It is...
2replies - ✓
Can you run a coding agent for free with a local model?
Yes, if your computer has the memory for a capable model. The open source Codex CLI has a built-in local mode for Ollama and LM Studio, and Ollama documents...
2replies - ✓
Claude Code, Codex or Copilot: how do coding agents differ?
Claude Code, Codex and GitHub Copilot are all coding agents that read a repository, edit files and run commands for you. They differ in maker, licence, the...
2replies - ✓
What is an MCP server, in plain terms?
An MCP server is a small program that gives an AI application a fixed menu of actions and data through the Model Context Protocol, an open standard. The AI app...
2replies - ✓
Is Playwright MCP worth it for testing vibe-coded apps?
Yes for exploring, no as your test suite. Playwright MCP lets an assistant drive a real browser and read the page as an accessibility snapshot, which is good...
2replies - ✓
How do you add skills to Claude Code?
You add a skill to Claude Code by creating a folder that holds a SKILL.md file, either in ~/.claude/skills/ for all your projects or in .claude/skills/ inside...
2replies - ✓
Which token scopes does the GitHub MCP server need?
Only the scopes for the tools you turn on. With a classic token, repo covers most repository, issue and pull request tools; add workflow, gist, notifications...
2replies - ✓
How do you sandbox the Filesystem MCP server?
Give it one project folder and nothing more. Pass that folder as the only allowed directory, or run the Docker image with the folder bind-mounted under...
2replies - ✓
Remote or local GitHub MCP server: which should you run?
Run the remote server if you use github.com and your client supports remote MCP servers: there is nothing to install, and OAuth asks for scopes as tools need...
2replies - ✓
How do you build a simple MCP server?
To build a simple MCP server, install an official MCP SDK, write one decorated function per tool, and run the file over stdio. In Python that is the mcp...
2replies