What is this project?
It is a small demo project designed to help you understand and set up a real MCP service.
@hellozhangran
Basic information
obsidian-mcp-python, a very simple MCP Server demo that can help you to operate something about your obsidian md file
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"obsidian-mcp-python": {
"command": "uv",
"args": [
"--directory",
"/path/of/your/project/file/obsidian-mcp-python",
"run",
"main.py"
],
"env": {
"OBSIDIAN_PATH": "/path/of/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.
Obsidian MCP Python is a small demo project that helps you understand the Model Context Protocol (MCP). It enables quick setup of a real MCP service connecting to an Obsidian vault. It is intended for developers (via a tutorial) and ordinary users who want to try it.
Clone the repository, install the uv tool on your local machine, then copy the provided JSON configuration into your MCP client (Cursor, Windsurf, or Claude Desktop). Adjust the directory paths and set the OBSIDIAN_PATH environment variable to point to your Obsidian vault.
uv toolIt is a small demo project designed to help you understand and set up a real MCP service.
Clone the repo, install `uv`, then add the provided JSON config to your MCP client, updating paths and the `OBSIDIAN_PATH` environment variable.
The README shows configuration examples for Cursor, Windsurf, and Claude Desktop.
Developers can look at the Tutorial.md file. Ordinary users should refer to the "Usage" section.
You must set `OBSIDIAN_PATH` to the path of your Obsidian vault.

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

Model Context Protocol Servers

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

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