What does MCP Server Obsidian Omnisearch do?
It provides a search tool that finds notes in your Obsidian vault using the Omnisearch plugin and returns their absolute file paths.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"anpigon_mcp-server-obsidian-omnisearch": {
"command": "python",
"args": [
"server.py",
"/path/to/your/obsidian/vault"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP Server Obsidian Omnisearch is a FastMCP-based server that exposes Obsidian vault search functionality through a REST API. It lets you programmatically search notes in your Obsidian vault using the Omnisearch plugin, returning absolute file paths of matching notes.
Install dependencies with uv install, then run the server by passing your vault path as a command‑line argument (e.g., python server.py /path/to/your/obsidian/vault). Configure it as an MCP tool in Claude Desktop using the provided claude_desktop_config.json snippet.
It provides a search tool that finds notes in your Obsidian vault using the Omnisearch plugin and returns their absolute file paths.
Python 3.x, an active Obsidian vault with the Omnisearch plugin installed and running, and the FastMCP library.
The vault path is supplied as a command‑line argument when starting the server, for example: `python server.py /path/to/your/obsidian/vault`.
It returns a list of absolute file paths for notes that match the search query.
The server runs over stdio and is designed to be used as an MCP tool (e.g., with Claude Desktop). No authentication is required.

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Model Context Protocol Servers
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

The official Semantic-UI-React integration
Comments