by jgravelle · MCP Server · ★ 162
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Stop Feeding Documentation Trees to Your AI Most AI agents still explore documentation the expensive way: open file → skim hundreds of irrelevant paragraphs → open another file → repeat That burns tokens, floods context windows with noise, and forces models to reason through a lot of text they never needed in the first place. jDocMunch-MCP lets AI agents navigate documentation by section instead of reading files by brute force. It indexes a documentation set once, then retrieves exactly the section the agent actually needs, with byte-precise extraction from the original file. Index once. Query cheaply forever. Precision context beats brute-force context. jDocMunch MCP AI-native documentation navigation for serious agents [ server that implements the Zettelkasten knowledge management methodology, allow
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM
Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Wi
Quickly reads webpages and converts to markdown for fast, token efficient web scraping
An md file as a chat interface and editable history in one.
Explore other popular mcp server tools:
jdocmunch-mcp is The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing. It is categorized as a MCP Server with 162 GitHub stars.
jdocmunch-mcp is primarily written in Python. It covers topics such as claude, claude-code, docs.
You can find installation instructions and usage details in the jdocmunch-mcp GitHub repository at github.com/jgravelle/jdocmunch-mcp. The project has 162 stars and 39 forks, indicating an active community.
The top alternatives to jdocmunch-mcp on Agent Skills Hub include zettelkasten-mcp, Ori-Mnemos, llm-wiki. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.