What environment variable must I set?
You must set `OBSIDIAN_VAULT_PATH` to the path of your Obsidian vault.
@zerogon1203
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"obsidian-mcp-server-zerogon1203": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}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-SERVER is a Model Context Protocol (MCP) Stdio server that allows LLM agents to interact with Obsidian. It provides Python‑based functions for managing Obsidian vaults and files.
Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, set the OBSIDIAN_VAULT_PATH environment variable to your Obsidian vault path, and run python main.py. You can then invoke JSON‑RPC methods (e.g., create_vault, list_vaults, write_vault_file) via stdio. For Cursor, add a configuration entry with the command pointing to your virtual environment’s Python and the script’s file path.
You must set `OBSIDIAN_VAULT_PATH` to the path of your Obsidian vault.
It uses the stdio transport.
Common error codes include: -32000 (general error), -32001 (vault not found), -32002 (vault already exists), -32003 (file not found), -32004 (path not found), -32005 (config file not found), -32006 (invalid config), -32007 (file operation error), -32008 (invalid request), -32009 (environment variable error), -32010 (Obsidian directory error).
Yes, the `create_vault` method accepts an optional `path` parameter.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

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

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

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable
Comments