Model Context Protocol (MCP): Hands-On with Agentic AI
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"mcp-hands-on-with-agentic-ai": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
The Model Context Protocol (MCP) allows developers to add agent behavior to LLMs by providing a universal protocol providing context to language models so they can interface with data and applications in a consistent way. MCP servers expose resources (data), tools (actions), and prompts (instructions) for the LLM and the user to use in performing more complex operations. In this repo you’ll explore how the MCP works in Claude Desktop to extend its functionality, and you’ll build your own MCP ser
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in education
A Model Context Protocol server for searching and analyzing arXiv papers
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
MCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with grounded, citation-backed answers from Gemini. Persistent auth, library management, cross-client sharing. Zero hallucinations, just your knowledge base.
Wikipedia MCP — wraps Wikipedia REST API (free, no auth)
MCP Security Weekly
Get CVE alerts and security updates for Mcp Hands On With Agentic Ai and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The Model Context Protocol (MCP) allows developers to add agent behavior to LLMs by providing a universal protocol providing context to language models so they can interface with data and applications in a consistent way. MCP servers expose resources (data), tools (actions), and prompts (instructions) for the LLM and the user to use in performing more complex operations. In this repo you’ll explore how the MCP works in Claude Desktop to extend its functionality, and you’ll build your own MCP servers using Python and TypeScript to give LLMs new capabilities to do things on the computer, connect with external APIs, and perform advanced multi-step actions.
You can work with these files in GitHub Codespaces or in an editor on your computer.
To run the MCP servers in development mode using the MCP Inspector and test them in Claude Desktop and Cursor, you need to clone the repository to your computer.
This repository contains folders with supporting files.
mcp-server-examples/text-assist: Python MCP server with tools to count characters and words in any given textmcp-server-examples/open-meteo-weather: Python MCP server with tools to get current and forecasted weather from Open-Meteomcp-server-examples/projectDocumenter: TypeScript MCP server with tools to summarize any project and generate comprehensive README.md documentsmcp-server-examples/gh-models-comparison: TypeScript MCP server with tools to list all available GitHub Models, compare models, and run completion comparisons between modelsgh-models-helper: Starting point for "Building an advanced MCP server using TypeScript"templates/mcp-server-python-template: README.md file with step-by-step instructions to set up a bare-bones MCP server using the Python MCP SDKtemplates/mcp-server-typescript-template: Scaffolding and instructions to set up a bare-bones MCP server using the TypeScript MCP SDKEach folder has a README.md file with installation instructions.
Inspired by the course Model Context Protocol (MCP): Hands-On with Agentic AI on LinkedIn Learning, created by Morten Rand-Hendriksen.