What dependencies does Obsidian MCP require?
Node.js v16 or higher, Obsidian Desktop, and the Obsidian Local REST API plugin must be installed and running.
@newtype-01
基本信息
This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deleting notes, as well as managing f
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Obsidian MCP is a Model Context Protocol (MCP) server that connects AI models to an Obsidian knowledge base, enabling direct reading, creating, updating, and deleting of notes, as well as folder management.
Ensure Obsidian is running with the Local REST API plugin installed and configured, then set environment variables (OBSIDIAN_VAULT_PATH, OBSIDIAN_API_TOKEN, OBSIDIAN_API_PORT). Run npm start to launch the server, which communicates with AI models via standard input/output.
Node.js v16 or higher, Obsidian Desktop, and the Obsidian Local REST API plugin must be installed and running.
Set environment variables: `OBSIDIAN_VAULT_PATH` (vault path), `OBSIDIAN_API_TOKEN` (API token from the plugin), and `OBSIDIAN_API_PORT` (default 27123). A `.env` file can be used and is gitignored.
It provides seven tools: `list_notes`, `read_note`, `create_note`, `update_note`, `search_vault`, `delete_note`, and `manage_folder`.
No. The server connects to an existing Obsidian vault via the Local REST API; all data remains in the vault and is not stored externally.
It uses standard input/output (stdio) for communication with AI models, as per the MCP specification.
Project context your AI can query through MCP — with source evidence.

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
评论