Summary

This project provides an Obsidian Model Context Protocol (MCP) server, enabling AI models to directly interact with Obsidian knowledge bases. It allows AI to read, write, and manage notes and folders, offering enhanced AI-driven knowledge management capabilities and strategic insights for developers and power users.

How It Works

The MCP server acts as a bridge, translating AI requests into actions within an Obsidian vault via the Obsidian Local REST API plugin. It supports core note and folder operations, advanced text replacement, and precision editing at heading or block-level. A dual API strategy combines the REST API with filesystem fallback for robustness. Features like intelligent search and context optimization (summarization) prepare data for LLMs.

Quick Start & Requirements

• Prerequisites: Node.js (v16+), Obsidian desktop app, and the Obsidian Local REST API plugin (configured with token and port).
• Primary Install: Remote Install via NPM: npx @huangyihe/obsidian-mcp. Other options include a one-click DXT package, global NPM install (npm install -g @huangyihe/obsidian-mcp), source clone, or Docker deployment.
• Configuration: Requires setting OBSIDIAN_VAULT_PATH, OBSIDIAN_API_TOKEN, and OBSIDIAN_API_PORT (default 27123).
• Links: Obsidian Local REST API plugin, NPM Package.

Highlighted Details

• AI-Powered Analysis: Leverages the TRILEMMA-PRINCIPLES framework for strategic insights, constraint identification, and solution generation.
• Auto Backlink Generation: Automatically scans the vault for note name mentions and converts them into Obsidian wikilinks.
• Precision Editing: Supports advanced PATCH operations targeting specific headings or block IDs (^block-id).
• Context Optimization: Implements smart content summarization to manage LLM context window limitations.

Maintenance & Community

• Creator: huangyihe.
• Community: Links provided to Prompt House (https://prompthouse.app/), YouTube (https://www.youtube.com/@huanyihe777), Twitter (https://x.com/huangyihe), and a Zsxq community (https://t.zsxq.com/19IaNz5wK).

Licensing & Compatibility

• License: MIT.
• Compatibility: Permissive MIT license allows for commercial use and integration into closed-source projects.

Limitations & Caveats

• Strict dependency on the Obsidian desktop application and the "Local REST API" plugin.
• The one-click DXT installation method requires a specific client environment.
• Newer features like AI analysis and auto-backlinking are marked as "NEW", suggesting potential for ongoing development and refinement.