1. Conduid
  2. RAG
  3. DocHarvest
MCP server · RAG

DocHarvest

by · github.com/RohannShetty/DocHarvest

Turn any documentation portal (GitBook, Mintlify, Docusaurus, ReadTheDocs) into LLM-ready Markdown, vector RAG JSONL, llms.txt, and styled offline PDFs. Zero-config CLI, desktop GUI & FastMCP server.

Unclaimed clidesktop-appdocumentation-scraperdocusaurusfpdf2gitbookllms-txtlocal-aimcp-servermintlifynextraoffline-docspdf-generatorragreadme-iosqlite-fts5vector-databasevitepress
InstallView source
34Low

Scored 21 days ago · breakdown

About DocHarvest

DocHarvest is an MCP server published by RohannShetty in the RAG category: turn any documentation portal (GitBook, Mintlify, Docusaurus, ReadTheDocs) into LLM-ready Markdown, vector RAG JSONL, llms.txt, and styled offline PDFs. Zero-config CLI, desktop GUI & FastMCP server.

The repository has 2 stars and 0 forks, with the last commit 3 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/RohannShetty/DocHarvest

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about DocHarvest

Powered by Claude · Grounded in docs

I know everything about DocHarvest. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v11.3.1v11.3.1 · 14 Oct 2026DocHarvest v11.3.1 A stabilization and hardening release ensuring zero hard browser dependencies and complete test suite synchronization across all surfaces. ✨ Features & Capabilities Zero-dependency browser fallback.**…
v11.3.0v11.3.0 · 6 Oct 2026DocHarvest v11.3.0 🧭 Brand System: one brand, generated everywhere** No feature change. This release exists because the product and its documentation had quietly become four different brands, and a brand kit drawn by hand would only have…
v11.2.0v11.2.0 · 28 Sep 2026DocHarvest v11.2.0 ✨ Features & Capabilities Full-content `llms-full.txt` is emitted beside `llms.txt` for every local and library capture, with deterministic page order and SHA-256 content hashes. `search_docs(..., max_tokens=...)` bounds…
v11.1.0v11.1.0 · 19 Sep 2026DocHarvest v11.1.0 Major feature release adding interactive multi-agent autonomous swarm tools, a universal 17+ harness skill installer, empirical AST token reduction benchmarks, zero-dependency browser GUI fallback, comprehensive…
v11.0.10v11.0.10 · 18 Sep 2026DocHarvest v11.0.10 Adds first-class support for running the DocHarvest Desktop GUI in any standard web browser (with automated detection and launch for Zen Browser, Google Chrome, Mozilla Firefox, or the system default), backed by an…
Questions

About DocHarvest

How do I install DocHarvest?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is DocHarvest safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is DocHarvest still maintained?

Yes — the latest release is v11.3.1 (14 Oct 2026), and the last commit was 3 days ago. The repository has 2 stars.