# Learn Mcp

> mcp server for Microsoft Learn

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

## Install

```sh
agentstack add mcp-softchris-learn-mcp
```

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

## About

# 🚀 MCP-Learn: Model Context Protocol Server

Welcome to **MCP-Learn**!  
Your friendly neighborhood Model Context Protocol (MCP) server 🦸‍♂️—making searches for Learn agentic

## ✨ Features

- ⚡ **Fast & Lightweight**: Blazing fast context handling.
- 🔒 **Secure**: Built-in authentication and authorization.
- 🔄 **Flexible Protocols**: Supports multiple context protocols.
- 🧩 **Extensible**: Easy to add your own plugins.
- 📊 **Metrics**: Real-time stats and monitoring.
- 🛠️ **Developer Friendly**: Clean API and great docs.

## 📦 Install

You're recommended to create a virtual environment for this project.

```bash
python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
```

Then, install the required packages:

```bash
git clone https://github.com/your-org/mcp-learn.git
cd mcp-learn
pip install requests "mcp[cli]"
```

## 🏃 Run

Start server with:

```bash
cd src
python server.py # should start a server on http://localhost:8000
```

Start client with:

```bash
python client.py
```

## Tools

- **learn_filter**, returns the filters available for Microsoft Learn.
- **free_text**, takes a parameters `query` and returns a list of search results from Microsoft Learn.
- **topic_search**, takes a parameter `topic` and `category` and returns a list of search results from Microsoft Learn. For example topic "Azure" and category "products".

## Use with Visual Studio Code

Use in Vs Code by adding an entry to *.vscode/mcp.json* and its "servers" section like so:

```json
{
  "servers": [
    {
      "type": "sse",
      "url": "http://localhost:8000/sse"
    }
  ]
}
```

In Agent mode, type a prompt like so:

```text
Do a free text search for JavaScript, use a tool
```

## License

This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

## 🤝 Contributing

Pull requests welcome! For major changes, please open an issue first.

Happy hacking! 🎉

## Source & license

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

- **Author:** [softchris](https://github.com/softchris)
- **Source:** [softchris/learn-mcp](https://github.com/softchris/learn-mcp)
- **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-softchris-learn-mcp
- Seller: https://agentstack.voostack.com/s/softchris
- 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%.