What task formats does Obsidian Tasks MCP Server support?
The server supports both Obsidian Tasks emoji format (e.g., `🗓️`, `⏳`, `📅`) and Dataview format for task metadata.
@jfim
基本情報
Obsidian tasks MCP server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"obsidian-tasks-mcp": {
"command": "npx",
"args": [
"@jfim/obsidian-tasks-mcp",
"/path/to/obsidian/vault"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
A Model Context Protocol (MCP) server that extracts and queries tasks from Obsidian markdown files using the Obsidian Tasks plugin format. Designed to enable AI-assisted task management with Claude via the MCP protocol.
Install globally via npm (npm install -g @jfim/obsidian-tasks-mcp) or run directly with npx. Specify the path to your Obsidian vault as a command-line argument when starting the server. Add the server configuration to your MCP-supporting client (e.g., Claude Desktop) using the JSON configuration shown in the README.
list_all_tasks and query_tasks.query_tasks tool with rich filter syntax (status, dates, tags, path, description, priority).The server supports both Obsidian Tasks emoji format (e.g., `🗓️`, `⏳`, `📅`) and Dataview format for task metadata.
Use `npx @jfim/obsidian-tasks-mcp /path/to/obsidian/vault`. No installation required.
It uses Obsidian Tasks query syntax. Filters include `done`/`not done`, date operators (e.g., `due today`, `due before YYYY-MM-DD`), tag filters (`tag includes #tag`), path filters, description filters, and priority filters.
Yes. Build the Docker image from the repository and run with a bind mount to your vault. Example configuration for Claude Desktop is included.
Yes. Run `npm test` to execute the test suite. See `TESTING.md` for more details.

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

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.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

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.
コメント