zotero-fulltext-mcp

matthiaskloft/zotero-fulltext-mcp

★ 0 stars Python Database Updated 3d ago

Convert a Zotero library's linked PDF attachments to Markdown, build a full-text search index, and expose it via an MCP server.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "zotero-fulltext-mcp": {
      "command": "uvx",
      "args": [
        "zotero-fulltext-mcp"
      ]
    }
  }
}

Or install with pip: pip install zotero-fulltext-mcp

README Excerpt

Convert a Zotero library's linked PDF attachments to Markdown, build a full-text search index, and expose it to LLM tools (Claude Code, Codex, etc.) through an MCP server — so an assistant can search and read your papers' full text, not just their metadata. The pipeline is read-only with respect to Zotero: it never writes to your live `zotero.sqlite`

📊

Working with market or time-series data?

The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.

View dataset →

zotero-fulltext-mcp

Quick Install

README Excerpt

Related Database Servers