What environment variables are required?
`API_KEY` (your Obsidian Local REST API secret key) is required. `API_HOST` (default `localhost`) and `API_PORT` (default `27124`) are optional.
@OleksandrKucherenko
基本情報
MCP Server connected to Obsidian Vault with Local REST API. (re-write it completely with BUN to make it faster and more lightweight)
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": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"API_KEY",
"-e",
"API_URLS",
"ghcr.io/oleksandrkucherenko/obsidian-mcp:latest"
],
"env": {
"API_KEY": "<your-obsidian-api-key>",
"API_URLS": "[\"https://host.docker.internal:27124\"]"
}
}
}
}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。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
mcp-obsidian is a Model Context Protocol (MCP) server that connects AI assistants to the Obsidian Local REST API, enabling programmatic access to Obsidian notes via a Docker container or local TypeScript runtime.
Configure the server in your MCP client’s JSON settings with required environment variables (API_KEY, API_HOST, API_PORT). The recommended deployment is via Docker using the image ghcr.io/oleksandrkucherenko/obsidian-mcp:latest. For local development, run bun run src/index.ts with the appropriate config.
--rm).DEBUG=mcp:* environment variable.`API_KEY` (your Obsidian Local REST API secret key) is required. `API_HOST` (default `localhost`) and `API_PORT` (default `27124`) are optional.
Run `curl --insecure https://localhost:27124` or use `netstat -an | findstr 27124` on Windows. For WSL2, use the gateway IP (`172.26.32.1` by default).
Yes. The README provides detailed firewall configuration, gateway IP detection, and connectivity tests for WSL2 with Obsidian running on the Windows host.
The default host is `localhost` and the default port is `27124`. Override via `API_HOST` and `API_PORT` environment variables.
Yes, for development you can run `bun run src/index.ts` after installing dependencies with `bun install`. Docker is recommended for production use.

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
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.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

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