What dependencies does Obsidian MCP Server require?
It requires Node.js 18 or later and read/write access to an Obsidian vault (Markdown files). The server is built on Express.js and uses the gray‑matter library for YAML frontmatter.
@smith-and-web
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"obsidian": {
"command": "npx",
"args": [
"@smith-and-web/obsidian-mcp-server"
],
"env": {
"VAULT_PATH": "/path/to/your/vault",
"PORT": "3001"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Obsidian vault. It allows you to access notes, create content, manage tags, and search your knowledge base through natural conversation.
Run the server via npx with the VAULT_PATH environment variable, or deploy with Docker. It exposes an SSE endpoint (port 3000 by default) that MCP clients like Claude Desktop or Cursor can connect to using mcp-remote. Configure the server in your AI assistant’s MCP settings pointing to the SSE URL.
It requires Node.js 18 or later and read/write access to an Obsidian vault (Markdown files). The server is built on Express.js and uses the gray‑matter library for YAML frontmatter.
It reads and writes directly to the vault directory you mount at startup. No external database is used; all data lives in your existing `.md` files.
Yes, the server supports optional API key authentication. When `API_KEY` is set, all `/sse` and `/message` endpoints require a Bearer token or `api_key` query parameter. The `/health` endpoint remains public.
It uses Server‑Sent Events (SSE) for real‑time communication. Clients connect to `/sse` and can send messages via POST to `/message`. A direct MCP call endpoint is also available at `/sse` (POST).
The server offers a compact response mode to reduce token usage. For large vaults, using `get-notes-info` instead of reading content improves efficiency. Full read/write access to the vault means caution is needed; delete operations require confirmation.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

The official Semantic-UI-React integration

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

MCP connector for Snipara, the Project Brain for AI coding agents
Comments