What is required to use Obsidian Mcp?
You must have Obsidian installed with the Obsidian Local REST API plugin enabled and configured, plus an API key for that plugin.
@orvice
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"experimental": {
"modelContextProtocol": true
},
"mcpServers": {
"obsidian-mcp": {
"command": "obsidian-mcp",
"args": [],
"env": {
"OBSIDIAN_BASE_URL": "http://localhost:27123",
"OBSIDIAN_API_KEY": "your-obsidian-api-key"
}
}
}
}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.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Obsidian Mcp is a Go-based Model Context Protocol server that connects MCP-compatible clients to Obsidian through the Obsidian Local REST API plugin. It is built for users who want to interact programmatically with their Obsidian notes from tools like Claude Desktop.
Install via go install or build from source, then set the OBSIDIAN_BASE_URL and OBSIDIAN_API_KEY environment variables. Start the server and use it with any MCP-compatible client, such as Claude Desktop or Continue, by adding it to the client’s MCP configuration.
You must have Obsidian installed with the Obsidian Local REST API plugin enabled and configured, plus an API key for that plugin.
The server supports both stdio (default) and SSE server mode. Enable SSE by setting the `SSE_SERVER` environment variable to `"true"`.
All data stays in your local Obsidian vault; the server acts as a bridge to the Obsidian REST API plugin, which runs locally on your machine.
Yes, the README provides configuration examples for Claude Desktop and Continue, and it should work with any MCP-compatible client that supports the stdio or SSE transports.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

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
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

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

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
Comments