pdf-cite-mcp

xultrax-web/pdf-cite-mcp

★ 0 stars Python 💻 Code/Dev Tools Updated 4d ago

MCP server for PDFs — every extraction returns precise {page, bbox, snippet} citations. Cite your sources.

View on GitHub → Try with Claude — $10 free →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "pdf-cite-mcp": {
      "command": "uvx",
      "args": [
        "pdf-cite-mcp"
      ]
    }
  }
}

Or install with pip: pip install pdf-cite-mcp

README Excerpt

**Cite your sources.** A Model Context Protocol server for PDFs that returns precise `{page, bbox, snippet}` citations on every extraction. Most PDF extraction returns text. **pdf-cite-mcp returns text AND the rectangle on the page where it came from.** Every tool's response includes `{page, bbox, snippet, confidence}` citations so an agent can ground every claim in a verifiable region — and a human can double-click to confirm in two seconds.

Tools (9)

PDF_CITE_CACHE_DIRpdf_doctorpdf_extract_tablespdf_infopdf_ocr_pagespdf_quotepdf_read_pagespdf_render_pagepdf_search

pdf-cite-mcp

Quick Install

README Excerpt

Tools (9)

Related Code/Dev Tools Servers