---
title: "doc-harvest"
description: "Harvest documentation websites into structured local references and navigate existing documentation sets."
canonical: https://agentpluginsdirectory.com/plugins/doc-harvest
last-updated: 2026-10-04
---

# doc-harvest
Harvest documentation websites into structured local references and navigate existing documentation sets.
- Slug: doc-harvest
- Publisher: Matthew Wagner
- Repository: https://github.com/mattwag05/mw-plugins
- Manifest: plugins/doc-harvest/plugin.json
- Version: 1.2.1
- License: MIT
- Category (editorial): research
- Skills: 2 (doc-harvest, doc-navigator)
- MCP servers: 1 (scrapling)
- Stars: 0
- Repository created: 2026-04-15
- Repository last pushed: 2026-09-22
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/doc-harvest
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- doc-harvest: Harvest a documentation website into a local, indexed reference set. Use for site discovery, batch scraping, content cleanup, and progressive-disclosure indexes.
- doc-navigator: Use when the user asks to "check the docs", "look up in docs", "what does the documentation say", "find in the docs", references a known harvested documentation set by name, or needs to navigate previously harvested documentation stored in the Claude Context Library.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- scrapling: transport: stdio; command: container run --rm -i pyd4vinci/scrapling@sha256:2a0c05bdd78211a76cb7ab9565a91250787a326f9ca73c97cf764ccb536631a2 mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.