The Obsidian MCP Server transforms your Obsidian vault into an AI-accessible knowledge management and automation hub with 30+ tools across these areas:
Navigation & Search
Browse, read, and get high-level vault overviews
Full-text/title search with AND logic, date-range filtering, and tag-based lookup
Note Management
Create, edit, append, move, rename, and delete notes
Insert content under specific headings, quick-capture ideas to Inbox with timestamps
Global find & replace with dry-run preview mode
Template support and AI-assisted folder placement suggestions
Vault Analysis
Comprehensive stats, recent activity summaries, tag analysis and canonical tag registry sync
Link analysis, backlinks, local graph visualization, and orphan note detection
AI Agent / Skills System
Define custom AI personalities/roles as skill files (
.agent/skills/)Load agent instructions, enforce global vault-wide rules, generate and sync skill files
Suggest personalized skills based on vault content patterns
Semantic Search (RAG)
Meaning-based search and non-obvious connection suggestions (requires optional
[rag]install)
External Content
Extract YouTube video transcripts to enrich your knowledge base
Security & Architecture
Vault-agnostic design with intelligent auto-detection
Sensitive folder protection (
.forbidden_paths)Compatible with Claude Desktop, Cursor, Cline, and other MCP clients
Connects AI to an Obsidian vault, enabling navigation, search, note creation with templates and smart tagging, context analysis of vault structure, and agent-based operations like reorganizing notes and discovering connections between them.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Obsidian MCP Servercreate a note about quantum computing basics using the research template"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Obsidian MCP Server
👁 License: MIT
👁 Python 3.11+
👁 MCP Compatible
👁 Obsidian Integration
👁 Claude Desktop
👁 Custom Skills
An MCP (Model Context Protocol) server that makes an Obsidian vault useful to AI clients such as Claude Desktop, Claude Code, Cursor, and Cline. It is designed as a public, reusable core with optional tool sets and vault-specific profiles layered on top.
Features
Public Core
The core tool set is always available and stays vault-agnostic:
Vault diagnostics, task routing, and MCP client root inspection.
Note listing, reading, metadata inspection, and search.
Vault context resources for profiles, skills, standards, and local docs.
Core prompts for structured notes, template usage, and context exploration.
Optional Tool Sets
Optional packs are enabled explicitly from .agents/vault.yaml or
OBSIDIAN_MCP_TOOL_SETS:
notes_write: Create, patch, move, and delete notes.vault_analysis: Vault statistics, tags, links, backlinks, and graph tools.agents_admin: Skill creation, validation, and cache management.youtube: Transcript extraction.obsidianrag: Semantic search through the external ObsidianRAG service.canvas/kanvas: Canvas and workflow helpers.Profile packs: Personal workflows only when a vault profile opts in.
Design Principles
Public core, personal profiles: The repository remains reusable; local workflows live in vault configuration and resources.
English technical surface: Tool names, prompt names, docs, and code identifiers are English.
Safe by default: Write tools are opt-in, protected paths are blocked, and large reads are capped.
External RAG by integration: Advanced semantic search delegates to ObsidianRAG instead of duplicating a RAG stack inside the MCP server.
Quick Setup
Prerequisites
Python 3.11+
uv (Recommended)
Steps
Clone:
git clone https://github.com/Vasallo94/obsidian-mcp-server.git cd obsidian-mcp-serverInstall:
make install # Optional legacy in-process semantic stack: pip install "obsidian-mcp-server[rag]"Configure:
cp .env.example .env # Edit .env with the absolute path to your Obsidian vault
Usage
The MCP server connects to compatible clients using the uv run obsidian-mcp-server command. Below are setup instructions for popular AI clients.
Claude Desktop Integration
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"obsidian": {
"command": "uv",
"args": ["run", "obsidian-mcp-server"],
"env": {
"OBSIDIAN_VAULT_PATH": "/Absolute/Path/To/Your/Vault"
}
}
}
}Optional Tool Sets
Enable optional tools from the client environment:
{
"env": {
"OBSIDIAN_VAULT_PATH": "/Absolute/Path/To/Your/Vault",
"OBSIDIAN_MCP_TOOL_SETS": "notes_write,vault_analysis,obsidianrag"
}
}Or declare them in your vault profile:
profile:
name: "my_profile"
prompt_sets:
- "mermaid"
tool_sets:
- "notes_write"
- "vault_analysis"
standards:
media: "Standards/Media.md"
local_docs:
index: "README.md"ObsidianRAG Integration
For semantic vault search, enable the obsidianrag tool set and declare the
integration:
profile:
tool_sets:
- "obsidianrag"
integrations:
obsidianrag:
project_path: "/path/to/ObsidianRAG"
api_url: "http://127.0.0.1:8000"
env:
OBSIDIANRAG_LLM_MODEL: "gemma3"
OBSIDIANRAG_OLLAMA_EMBEDDING_MODEL: "embeddinggemma"Then read obsidian://integrations/obsidianrag/setup or call
rag.setup_status. Agents should show setup commands before installing
dependencies, starting services, pulling models, or rebuilding the index.
Cursor & Cline Integration
For other clients like Cursor or Cline, you can add it as a new MCP server in their settings panel by specifying:
Type:
commandCommand:
uv run obsidian-mcp-serverEnsure the
OBSIDIAN_VAULT_PATHenvironment variable is available to the instance running the command.
Technical Documentation
To dive deeper into how the server works and how to customize it, check our detailed guides located in the docs/ folder:
Architecture: Modular structure and data flow of the project.
Tool Reference: Complete list of available MCP tools and their parameters.
Server Configuration: Guide on environment variables and technical configuration.
Agent Setup: How to organize your vault (
.agents/) with skills and contextual rules.Semantic Search: ObsidianRAG integration and legacy RAG migration notes.
Future Roadmap: Planned improvements and next steps for the server.
Development & Quality
Command | Description |
| Run the test suite (pytest) |
| Run static checks (Ruff + Mypy + Pylint) |
| Automatically format code |
| Run the MCP inspector for live testing |
License
This project is licensed under the MIT License.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Vasallo94/obsidian-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
