# Bearletter Docs

> What a Bearletter blog is made of, and how people and agents work with it.

Every page is Markdown. Open only the pages you need.

## Agents (MCP)

- [Connect an agent](https://docs.bearletter.com/mcp/connect.md): Add Bearletter as a remote MCP server, approve it in the browser, and check that it works.
- [Tools](https://docs.bearletter.com/mcp/tools.md): Every MCP tool by area, what it does and the permission it needs.
- [Skills and plugins](https://docs.bearletter.com/mcp/skills.md): The Bearletter skill and plugin, which add the MCP server and teach your agent how Bearletter works.

## Blog format

- [The blog folder](https://docs.bearletter.com/blog/folder.md): Which files a blog has, where posts, pages and episodes go, and how a path becomes an address.
- [Properties](https://docs.bearletter.com/blog/frontmatter.md): The key: value block at the top of a file, and every property each file accepts.
- [Components](https://docs.bearletter.com/blog/components.md): The lines that start with :: and what each one shows.
- [Themes](https://docs.bearletter.com/blog/themes.md): How styles.css is laid out, the variables themes share, light and dark modes, and the page's class names.
- [Podcast](https://docs.bearletter.com/blog/podcast.md): The podcast (Pro): podcast.md for the show and one file per episode in podcast/, with every property.

## API

- [Text API](https://docs.bearletter.com/api/text-api.md): Read and write blog files over HTTPS with a personal access token. Reading works on every plan; writing is part of Pro.
- [Backups](https://docs.bearletter.com/api/backup.md): Export everything to your own disk or storage on a schedule, with a read-only token. Works on every plan.
