Obsidian MCP
This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deletin
What is Obsidian MCP?
Obsidian MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this project implements a model context protocol (mcp) server for connecting ai models with obsidian knowledge bases. through this server, ai models can directly access and manipulate obsidian notes, ...
This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deletin
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This project implements a Model Context Protocol (MCP) serve
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx obsidian-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Obsidian MCP
Obsidian MCP is a Model Context Protocol server that gives AI models direct access to your Obsidian knowledge base through the Obsidian Local REST API plugin. It supports reading, creating, updating, deleting, moving, and searching notes, as well as heading-based edits, block ID targeting, and automatic wikilink generation across your entire vault. Developers and knowledge workers use it to let Claude or other AI assistants draft, organize, and cross-link notes directly in Obsidian without manual copy-pasting.
Prerequisites
- Obsidian desktop application installed with a vault configured
- The 'Local REST API' community plugin installed and enabled in Obsidian (generate an API token in its settings)
- Node.js and npm installed
- An MCP-compatible AI client such as Claude Desktop or Cursor
Install the Local REST API plugin in Obsidian
Open Obsidian, go to Settings > Community Plugins, search for 'Local REST API', install and enable it. In the plugin settings, generate an API token and note the port number (default: 27123).
Install the obsidian-mcp server package
Install the package globally using npm, or use npx to run it without a global install. The package name on npm is @huangyihe/obsidian-mcp.
npm install -g @huangyihe/obsidian-mcpAdd the MCP server to your AI client configuration
Open your AI client's MCP config file and add an entry for obsidian-mcp. Set the three required environment variables: your vault path, the API token from the Local REST API plugin, and the port number.
{
"mcpServers": {
"obsidian-mcp": {
"command": "npx",
"args": ["@huangyihe/obsidian-mcp"],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault",
"OBSIDIAN_API_TOKEN": "your_token_from_plugin_settings",
"OBSIDIAN_API_PORT": "27123"
}
}
}
}Ensure Obsidian is running with the plugin active
The Local REST API plugin only serves requests while Obsidian is open and running. Make sure Obsidian is launched before using the MCP server, as it needs the REST API to be reachable at the configured port.
Restart your AI client and verify the tools
Fully restart your AI client so it starts the obsidian-mcp server process. Check that the Obsidian tools appear in the tools list, then test by asking the AI to list notes in your vault.
Obsidian MCP Examples
Client configuration
Claude Desktop configuration for obsidian-mcp. All three OBSIDIAN_ environment variables are required — the server will fail to start without them.
{
"mcpServers": {
"obsidian-mcp": {
"command": "npx",
"args": ["@huangyihe/obsidian-mcp"],
"env": {
"OBSIDIAN_VAULT_PATH": "/Users/me/Documents/MyVault",
"OBSIDIAN_API_TOKEN": "your_local_rest_api_token",
"OBSIDIAN_API_PORT": "27123"
}
}
}
}Prompts to try
After connecting, use these prompts to interact with your Obsidian vault through Claude or another AI client.
- "List all notes in my vault that mention 'machine learning'"
- "Create a new note called 'Meeting Notes 2026-06-13' with today's agenda"
- "Search my vault for notes about project planning and summarize them"
- "Add a section called 'Next Steps' to my 'Current Projects' note"
- "Find all notes that reference 'authentication' and add wikilinks between them"Troubleshooting Obsidian MCP
Connection refused or API token errors when the server starts
Confirm Obsidian is running and the Local REST API plugin is enabled. Verify the OBSIDIAN_API_TOKEN matches the value shown in the plugin settings, and that OBSIDIAN_API_PORT matches the port the plugin is listening on (check the plugin settings for the exact port).
Environment variables not recognized — server fails with a config error
Ensure all three env vars use the exact OBSIDIAN_ prefix: OBSIDIAN_VAULT_PATH, OBSIDIAN_API_TOKEN, and OBSIDIAN_API_PORT. Variables without this prefix are ignored. Double-check for typos in the JSON config.
Notes are not found even though they exist in the vault
Verify that OBSIDIAN_VAULT_PATH points to the exact root folder of the vault (the folder that contains the .obsidian directory). Relative paths may not resolve correctly — use an absolute path.
Frequently Asked Questions about Obsidian MCP
What is Obsidian MCP?
Obsidian MCP is a Model Context Protocol (MCP) server that this project implements a model context protocol (mcp) server for connecting ai models with obsidian knowledge bases. through this server, ai models can directly access and manipulate obsidian notes, including reading, creating, updating, and deletin 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 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.