What kind of search does it perform?
It performs semantic search over indexed notes in the Obsidian vault.
@tcsavage
基本信息
MCP server providing sementic search over Obsidian vaults
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-obsidian-index": {
"command": "uv",
"args": [
"run",
"obsidian-index",
"mcp",
"--vault",
"<VAULT_PATH>",
"--database",
"<DATABASE_PATH>",
"--reindex",
"--watch"
]
}
}
}Performs semantic search over indexed notes
Obsidian Index MCP server is an MCP server that provides semantic search over an Obsidian vault and exposes recently modified notes as resources. It is designed for users of Obsidian who want to integrate semantic search and note retrieval into MCP-compatible tools.
Install via PyPI using uv run obsidian-index or uvx obsidian-index. Launch the server with --vault <VAULT_PATH>, --database <DATABASE_PATH>, --reindex, and --watch flags. The server exposes one tool (search-notes) and the recent notes as resources.
obsidian:// URL scheme with text/markdown MIME type.--vault flag.--watch.--reindex flag.It performs semantic search over indexed notes in the Obsidian vault.
Use `uv run obsidian-index mcp --vault <VAULT_PATH> --database <DATABASE_PATH> --reindex --watch` in your terminal.
Add a JSON entry to `claude_desktop_config.json` using the `uv` or `uvx` command with the appropriate arguments (see Quickstart section in the README).
The server requires Python (with the package installed via `uv`) and the Obsidian Index package itself. No additional runtime dependencies are listed.
Use the MCP Inspector: run `npx @modelcontextprotocol/inspector uv --directory <PATH_TO_PROJECT> run obsidian-index`.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

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

Model Context Protocol Servers

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
评论