About Obsidian MCP Module
Obsidian MCP Module is an MCP server for accessing notes in Obsidian vaults. It offers both tools and resources, accommodating clients that support only one access method.
Key features
- 01Search notes by topic
- 02Retrieve note contents
- 03Expose notes as tools and resources
Use cases
- 01Find notes related to a topic
- 02Read a note from an Obsidian vault
MCP support
It exposes Obsidian vault notes to MCP clients through search and retrieval tools, as well as resources.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEObsidian MCP Module
This module provides an MCP server for reading Obsidian vaults.
Currently both MCP tools and resources exist for accessing notes since some clients only support one or the other (VS Code only support tools).
Features
search-notes: Search notes by topicget-note: Retrieve note contents
Installation
The Obsidian Metadata Extractor plugin needs to be enabled in order to create the metadata.json file this MCP server uses.
VS Code
You'll need to add a .vscode/mcp.json file to your workspace. Or you can set it up so all workspaces have access: https://code.visualstudio.com/docs/copilot/chat/mcp-servers.
{
"servers": {
"obsidian-mcp": {
"type": "stdio",
"command": "deno",
"args": [
"run",
"--allow-read",
"${workspaceFolder}/main.ts",
"--vaultPath=/path/to/vault"
]
}
}
}
Claude Desktop
{
"mcpServers": {
"filesystem": {
"command": "/path/to/deno",
"args": [
"run",
"--allow-read",
"/path/to/main.ts",
"--vaultPath=/path/to/vault"
]
}
}
}
License
This project is licensed under the MIT License. See the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.