Obsidian Hybrid Search
@flowing-abyss
About Obsidian Hybrid Search
Local-first MCP server for searching private Obsidian vaults with hybrid full-text, fuzzy, semantic, and wikilink graph retrieval.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"obsidian-hybrid-search": {
"command": "npx",
"args": [
"-y",
"-p",
"obsidian-hybrid-search@latest",
"obsidian-hybrid-search-mcp"
],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault"
}
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Obsidian Hybrid Search?
Obsidian Hybrid Search is a local-first MCP server for searching private Obsidian vaults. It supports hybrid retrieval methods including full-text, fuzzy, semantic, and wikilink graph searches.
How to use Obsidian Hybrid Search?
—
Key features of Obsidian Hybrid Search
- Local‑first architecture for privacy.
- Supports full‑text, fuzzy, semantic, and wikilink graph search.
- Designed specifically for private Obsidian vaults.
Use cases of Obsidian Hybrid Search
- Search notes across an Obsidian vault using multiple retrieval strategies.
- Perform private, offline search without sending data to external services.
FAQ from Obsidian Hybrid Search
What search methods does it support?
It supports full‑text, fuzzy, semantic, and wikilink graph retrieval.
Is the server local‑first?
Yes, it is described as local‑first, meaning data stays on your machine.
What kind of vaults can it search?
It is built for private Obsidian vaults.
What are the runtime or dependency requirements?
—
Which transport or authentication does it use?
—
Frequently asked questions
What search methods does it support?
It supports full‑text, fuzzy, semantic, and wikilink graph retrieval.
Is the server local‑first?
Yes, it is described as local‑first, meaning data stays on your machine.
What kind of vaults can it search?
It is built for private Obsidian vaults.
Basic information
More Memory & Knowledge MCP servers

Orcha
westonhancockOrcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
Groundwork
Rarefied-EarthGroundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
Context7 MCP - Up-to-date Docs For Any Cursor Prompt
upstashContext7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Memlord
MyrikLDMemlord is a remote MCP server available at https://app.memlord.com.
Mcp Knowledge Graph
shanehollomanMCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
Comments