Skip to main content

MCP Crash Course - A collection of MCP server examples including news reader, stock news agent, and Wikipedia summary agent

Project description

🧪 MCP Lab – Experiments with Anthropic's Model Context Protocol

Welcome to MCP Lab, a collection of projects, demos, and experiments using Model Context Protocol (MCP). This repository serves as a playground to explore the power and versatility of MCP in connecting AI models to external tools, data sources, and services.

Think of MCP as USB-C for AI – a standardized way to plug large language models (LLMs) into your tools with minimal custom code.


📂 Structure

Each folder in this repo represents an independent, self-contained project or tutorial built using MCP. Projects vary from beginner-friendly crash courses to deeper integrations with real-world APIs and local infrastructure.

mcp-lab/
│
├── mcp-crash-course/         # Introductory project – walk-through of MCP basics
├── Coming soon...

Each project includes:

  • Clear setup instructions
  • Source code for MCP servers and/or clients
  • Examples or video walkthroughs
  • Optional Claude or local LLM integration

🧠 Why MCP?

Model Context Protocol (MCP) enables:

  • 🔌 Plug-and-play integrations between LLMs and external tools
  • 🔒 Privacy-aware, local-first design (no need to expose your data to the cloud)
  • 🧱 Composable, reusable servers for Slack, GitHub, databases, and more
  • 🌐 LLM-agnostic architecture (works with Claude, Ollama, ChatGPT, etc.)

With MCP, you write a connector once, and any compatible model can use it. It’s the future of LLM-to-tool communication.


🛠 Getting Started

To run any project:

  1. Clone the repo:

    git clone https://github.com/Farzad-R/mcp-lab.git
    cd mcp-lab
    
  2. Navigate to the project folder you're interested in (e.g. mcp-crash-course)

  3. Follow the README.md inside that folder for setup and instructions


🎥 Related Video Series

All of these projects are featured in my educational videos on YouTube.

➡️ Watch the full crash course: [MCP Crash Course – YouTube Link]


🤝 Contributing

Want to add your own MCP experiment?
PRs are welcome! Follow the format of existing folders and include:

  • A clear README.md
  • A self-contained demo (scripts, server, or configs)
  • Optional: video or blog post link

MCP-Crash-Course YouTube Video: URL


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_farzad_r_mcp_lab-0.1.0.tar.gz (150.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iflow_mcp_farzad_r_mcp_lab-0.1.0-py3-none-any.whl (155.3 kB view details)

Uploaded Python 3

File details

Details for the file iflow_mcp_farzad_r_mcp_lab-0.1.0.tar.gz.

File metadata

  • Download URL: iflow_mcp_farzad_r_mcp_lab-0.1.0.tar.gz
  • Upload date:
  • Size: 150.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_farzad_r_mcp_lab-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a256705298393e17b8525a2947c58c11be9417924ab89f12c7d203ef19e396c7
MD5 fb15d7f8ee6322c7c5efa0b6ca727832
BLAKE2b-256 7db9f38f70ca9ea95e3dddfcfcc4b0365d586c37802b17b027c3820ceb81a549

See more details on using hashes here.

File details

Details for the file iflow_mcp_farzad_r_mcp_lab-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_farzad_r_mcp_lab-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 155.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_farzad_r_mcp_lab-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ca8f4c9d9a999c760e09e67098707847a526249d3bf0ceaf21e352e9aef90a4c
MD5 26e6b67274decafd1afa1b1004586062
BLAKE2b-256 f92e30847db1a7354742029a2cb7c6b448e48034f6d87ffeda1d8ab1c8b4ec93

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page