# MCP Relearn

This project provides a Python-based search functionality for static websites
generated by [Hugo](https://gohugo.io) using the [Relearn](https://github.com/McShelby/hugo-theme-relearn) theme. It enables AI-assisted search over documentation content, supporting integration with AI clients like [Jan](https://github.com/janhq/jan) and local [Ollama](https://ollama.com) instances.

The library implements search engines using different backends:
- **Lunr**: Full-text search using the `lunr.js` algorithm
- **RapidFuzz**: Fuzzy string matching for approximate results

## Scope

This project is designed as an MCP (Model Context Protocol) server that:
- Fetches and indexes search data from Hugo/Relearn-generated sites
- Provides semantic search capabilities over documentation content
- Supports multiple search backends for different use cases
- Integrates with AI chat clients for natural language queries

## Prerequisites

* Any **MCP client** able to provide tools to LLMs as MCP servers.
* **Python 3.14** runtime environment.
* A **static website** generated by [Hugo](https://gohugo.io) and using the
  fabulous **[Relearn](https://github.com/McShelby/hugo-theme-relearn) theme**.

## Licensing

See [LICENSE](./LICENSE)

---

## How to actually use this

### Using "Jan" and a remote Ollama instance

Instructions on how to set up a lean working environment using [Jan](https://github.com/janhq/jan)
as an AI Chat client and MCP host together with an [Ollama](https://github.com/ollama/ollama) instance – preferably self-hosted – can be found in [README-jan.md](./README-jan.md).