Obsidian MCP
High-performance Model Context Protocol (MCP) server for Obsidian that provides AI tools with direct vault access through semantic operations and HTTP transport.
What is Obsidian MCP?
Obsidian MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to high-performance model context protocol (mcp) server for obsidian that provides ai tools with direct vault access through semantic operations and http transport.
High-performance Model Context Protocol (MCP) server for Obsidian that provides AI tools with direct vault access through semantic operations and HTTP transport.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- High-performance Model Context Protocol (MCP) server for Obs
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx obsidian-mcp-pluginConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Obsidian MCP
The Obsidian MCP Plugin is a high-performance Model Context Protocol server built directly into Obsidian as a community plugin, giving AI clients like Claude direct access to your local vault over HTTP or HTTPS transport. It exposes eight semantic tool groups covering note reading, writing, editing, semantic search, graph traversal, Dataview DQL queries, Bases views, and system commands — allowing AI assistants to find connections across notes, summarize research, and make targeted edits without leaving the vault. Unlike remote MCP servers, all data stays local because the plugin runs inside the Obsidian process on your own machine.
Prerequisites
- Obsidian desktop app installed with a vault you want to expose
- Community plugins enabled in Obsidian (Settings → Community plugins → turn off Safe mode)
- An MCP-compatible AI client: Claude Desktop, Claude Code, or Continue.dev
- For HTTPS access: willingness to add a self-signed certificate to your OS trust store
Install the plugin from Community plugins
Open Obsidian Settings → Community plugins → Browse, search for 'Semantic Notes Vault MCP', click Install, then click Enable.
Note the server ports and generate an API key
After enabling, open the plugin settings. The plugin runs an HTTP server on port 3001 and HTTPS on port 3443. Copy the API key shown in the settings — you will need it for client authentication.
Configure Claude Desktop with the .mcpb bundle
In the plugin settings, download the .mcpb bundle and drag it onto the Claude Desktop window to auto-configure the connection. Alternatively, add the HTTP entry manually.
Configure Claude Code manually
For Claude Code, add the MCP server using the HTTP transport pointing to the local plugin server. Replace YOUR_API_KEY with the key from the plugin settings.
claude mcp add obsidian-vault --transport http --url http://localhost:3001 --header "Authorization: Bearer YOUR_API_KEY"Trust the self-signed certificate (HTTPS only)
If you choose HTTPS (port 3443), the plugin auto-generates a self-signed certificate at .obsidian/plugins/semantic-vault-mcp/certificates/default.crt. On macOS, add it to the system keychain. For Claude Code/Bun, set the NODE_EXTRA_CA_CERTS environment variable to point to the certificate file.
export NODE_EXTRA_CA_CERTS="/path/to/your/vault/.obsidian/plugins/semantic-vault-mcp/certificates/default.crt"Verify with a semantic search
In your AI client, ask it to search your vault for a topic. A successful response with relevant notes confirms the connection is working.
Obsidian MCP Examples
Client configuration
Manual JSON configuration for Claude Desktop or another MCP client using HTTP transport to the local Obsidian plugin.
{
"mcpServers": {
"obsidian-vault": {
"transport": "http",
"url": "http://localhost:3001",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Prompts to try
Try these prompts once the plugin is running and your AI client is connected.
- "Summarize all my notes tagged #research and identify common themes"
- "Find every note that links to the 'Machine Learning' note and describe how they are connected"
- "Search my vault for notes about productivity systems written in the last 30 days"
- "Run a Dataview query to list all tasks that are not yet completed across my vault"
- "Create a new note called 'Weekly Review 2026-06-13' and populate it with a template based on my previous weekly reviews"Troubleshooting Obsidian MCP
AI client cannot connect to localhost:3001 or gets a connection refused error
Ensure the plugin is enabled in Obsidian and Obsidian is running. Open the plugin settings and confirm the HTTP server status shows 'Running'. If a firewall is blocking the port, add an exception for port 3001.
Authentication errors or 401 Unauthorized responses
Copy the API key exactly from the plugin settings page — it is case-sensitive. In your MCP client config, ensure the Authorization header is formatted as 'Bearer YOUR_API_KEY' with no extra spaces or newlines.
HTTPS certificate errors when using port 3443
The plugin generates a self-signed certificate. You must add it to your OS trust store (macOS Keychain) or set NODE_EXTRA_CA_CERTS to the certificate path for Node.js-based clients like Claude Code.
Frequently Asked Questions about Obsidian MCP
What is Obsidian MCP?
Obsidian MCP is a Model Context Protocol (MCP) server that high-performance model context protocol (mcp) server for obsidian that provides ai tools with direct vault access through semantic operations and http transport. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Obsidian MCP?
Follow the installation instructions on the Obsidian MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Obsidian MCP?
Obsidian MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Obsidian MCP free to use?
Yes, Obsidian MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Obsidian MCP Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Obsidian MCP? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Obsidian MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Obsidian MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.