Metadata-Version: 2.4
Name: anthology-mcp
Version: 0.1.2
Summary: MCP server for Anthology — scrape documentation sites into AI-ready Markdown
Author: Rajat Khandelwal
License-Expression: AGPL-3.0-only
Project-URL: Homepage, https://github.com/rajat10cube/Anthology
Project-URL: Repository, https://github.com/rajat10cube/Anthology
Project-URL: Issues, https://github.com/rajat10cube/Anthology/issues
Keywords: mcp,llm,documentation,scraper,markdown,ai
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Documentation
Classifier: Topic :: Text Processing :: Markup :: Markdown
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.27
Requires-Dist: beautifulsoup4>=4.12
Requires-Dist: markdownify>=0.12
Requires-Dist: mcp>=1.0
Requires-Dist: pydantic>=2.0
Requires-Dist: python-dotenv>=1.0
Requires-Dist: PyYAML>=6.0
Provides-Extra: playwright
Requires-Dist: playwright>=1.40; extra == "playwright"

# anthology-mcp

**MCP server for [Anthology](https://github.com/rajat10cube/Anthology)** — scrape any documentation website into AI-ready Markdown, directly from your AI coding assistant.

## Install

```bash
pip install anthology-mcp
```

## Usage with Claude Code

```bash
claude mcp add anthology -- anthology-mcp
```

Then ask Claude:

- *"Scrape the Supabase auth docs via Anthology, then write the login code for me."*
- *"What scraped docs do you have in Anthology right now?"*

## What it does

Anthology's MCP server exposes three tools to AI agents:

| Tool | Description |
|------|-------------|
| `scrape_new_docs` | Crawl a documentation site and convert it to Markdown |
| `read_scraped_docs` | Read previously scraped documentation |
| `list_scraped_docs` | List all saved documentation projects |

The scraper uses BFS crawling with sitemap discovery, configurable depth/page limits, and optional headless browser support for JS-heavy sites.

## Optional: Headless Browser

For JavaScript-rendered sites (Docusaurus, Mintlify, etc.):

```bash
pip install anthology-mcp[playwright]
playwright install chromium
```

## Links

- **GitHub**: [github.com/rajat10cube/Anthology](https://github.com/rajat10cube/Anthology)
- **License**: [AGPL-3.0](https://github.com/rajat10cube/Anthology/blob/main/LICENSE)
