What are the prerequisites for using this server?
Python 3.x, an active Obsidian vault with the Omnisearch plugin installed and running, and the FastMCP library.
@anpigon
Basic information
An MCP server that enables searches within Obsidian vaults using the Omnisearch plugin API. Returns absolute paths to matching notes for seamless integration. 🚀
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-obsidian-omnisearch": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@anpigon/mcp-server-obsidian-omnisearch",
"--client",
"claude"
]
}
}
}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.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
MCP Server Obsidian Omnisearch is a FastMCP-based server that provides programmatic search functionality for Obsidian vault notes through a REST API interface. It is designed for developers and power users who want to integrate Obsidian vault searches into other tools or workflows.
The server can be installed via Smithery or manually using uv. After installation, run the server with the path to your Obsidian vault as a command-line argument (e.g., python server.py /path/to/vault). Configure it as an MCP tool in an application like Claude Desktop by adding the appropriate configuration to claude_desktop_config.json. The server exposes a single tool, obsidian_notes_search(query), which returns absolute paths to matching notes.
uvPython 3.x, an active Obsidian vault with the Omnisearch plugin installed and running, and the FastMCP library.
Provide the absolute path to your vault as a command-line argument when starting the server.
It requires FastMCP, requests, and urllib libraries.
Use the MCP Inspector by running `npx @modelcontextprotocol/inspector` with the appropriate `uv` command, or watch server logs using `tail`.
The project is licensed under the MIT License.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

MCP connector for Snipara, the Project Brain for AI coding agents

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

One permissioned folder your team and your AI agents both log into.
Comments