# Intro To Agentic Ai Mcp Unsloth

> An introduction to agentic AI, MCP server development, and SLM fine-tuning - in easy to follow Jupyter notebooks.

- **Type:** MCP server
- **Install:** `agentstack add mcp-matthew-sayer-intro-to-agentic-ai-mcp-unsloth`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [matthew-sayer](https://agentstack.voostack.com/s/matthew-sayer)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [matthew-sayer](https://github.com/matthew-sayer)
- **Source:** https://github.com/matthew-sayer/intro_to_agentic_ai_mcp_unsloth

## Install

```sh
agentstack add mcp-matthew-sayer-intro-to-agentic-ai-mcp-unsloth
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Introduction to Agentic AI, MCP and fine-tuning Workshop - Matthew Sayer

Welcome to my intro to Agentic AI, MCP and fine-tuning workshop repo.

This set of workshops, packaged into easy to follow Jupyter notebooks, aims to introduce participants to Agentic Systems, MCP and fine-tuning, and start to demonstrate their application in solving real-world problems.

## Do the workbooks in this order:

### Recommended:
1. Run through mcp_intro.ipynb first and run your server.
2. Run all of the agentic_ai_intro.ipynb steps including the MCP server optional steps at the end.
3. Go to the fine_tuning_unsloth.ipynb notebook and complete the linked Colab notebook to learn how to fine-tune a small language model.

### Alternative (simplified)
1. Go straight to the agentic_ai_intro and run that on its own up to the Optional section at the end with MCP.

## Prerequisites

**_Required:_**

- Python 3.13+ with uv
- ollama

## Getting Started

1. Create and activate a virtual environment with uv (as shown in the notebooks)
2. Run the Jupyter notebook to build and execute the agent

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [matthew-sayer](https://github.com/matthew-sayer)
- **Source:** [matthew-sayer/intro_to_agentic_ai_mcp_unsloth](https://github.com/matthew-sayer/intro_to_agentic_ai_mcp_unsloth)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-matthew-sayer-intro-to-agentic-ai-mcp-unsloth
- Seller: https://agentstack.voostack.com/s/matthew-sayer
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.