Shelfmark

Overview

Shelfmark is a Model Context Protocol (MCP) server: Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG. In practice that means any MCP-compatible AI assistant can call Shelfmark's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package shelfmark (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.4.9, published under the MIT license, with source at Dankaro-projects/shelfmark on GitHub.

Shelfmark is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Shelfmark for Dankaro-projects, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "shelfmark": {
      "command": "uvx",
      "args": [
        "shelfmark"
      ]
    }
  }
}