# pdfplumber MCP Server

Extract tables, text, and metadata from PDFs using pdfplumber. Connect from Claude Desktop, Cursor, Windsurf, or any MCP client.

## Tools Available

### extract_text
Extract all text from a PDF.
- url: PDF URL (required)
- pages: Page range like "1-3", "1,3,5", or "all" (default: all)

### extract_tables
Extract tables as structured data.
- url: PDF URL (required)
- pages: Page range (default: all)
- output_format: json, markdown, or csv (default: markdown)

### extract_metadata
Get PDF info: page count, title, author, dates.
- url: PDF URL (required)

## MCP Client Configuration

```json
{
  "mcpServers": {
    "pdfplumber": {
      "url": "https://actors.apify.com/vibexcoder/pdfplumber-mcp-server/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}
```

## Use Cases
- Extract financial tables from earnings reports
- Pull data from invoices
- Convert PDF reports to structured data
- RAG pipelines needing clean PDF text