How does Obsidian MCP Server compare to other Obsidian MCP solutions?
This implementation is intentionally lightweight and standalone. Alternatives like jacksteamdev/obsidian-mcp-tools offer a more feature-rich approach as an Obsidian plugin.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"marcelmarais_obsidian-mcp-server": {
"command": "node",
"args": [
"obsidian-mcp-server/build/index.js",
"/path/to/your/vault"
]
}
}
}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 Server is a lightweight Model Context Protocol (MCP) server that enables AI assistants such as Cursor and Claude to read from and write to your Obsidian vault. It provides direct filesystem access without requiring the Obsidian application to be running, making it suitable for users who want AI-driven note management and automation.
Install via npm (npm install obsidian-mcp-server), build (npm run build), then configure the server in Claude Desktop or Cursor by pointing to the compiled index.js file and your vault’s file path. Example commands are provided for both Claude Desktop and Cursor.
This implementation is intentionally lightweight and standalone. Alternatives like jacksteamdev/obsidian-mcp-tools offer a more feature-rich approach as an Obsidian plugin.
No, the server accesses the vault’s files directly on the filesystem, so Obsidian does not need to be open.
Run `npm install obsidian-mcp-server` and `npm run build`. Then add the server to your Claude Desktop or Cursor configuration, specifying the path to the built `index.js` and your vault directory.
It provides four tools: `getAllFilenames` (list files), `readMultipleFiles` (read file contents), `getOpenTodos` (find unchecked todos), and `updateFileContent` (create/update files).
The server reads and writes directly to the markdown files in your Obsidian vault. No external cloud storage is used, and your data stays on your local filesystem.

The official Semantic-UI-React integration
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
评论