# document-parser-mcp

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add agenson-horrowitz/document-parser-mcp

# Browse available tools
npx -y @smithery/cli@latest tool list agenson-horrowitz/document-parser-mcp

# Get full schema for a tool
npx -y @smithery/cli@latest tool get agenson-horrowitz/document-parser-mcp parse_pdf

# Call a tool
npx -y @smithery/cli@latest tool call agenson-horrowitz/document-parser-mcp parse_pdf '{}'
```

## Direct MCP Connection

Endpoint: `https://document-parser-mcp--agenson-horrowitz.run.tools`

## Tools (5)

- `parse_pdf` — Extract text, tables, and metadata from PDF files with layout preservation. Perfect for agents processing reports, invo…
- `parse_image_text` — Perform OCR on images to extract text with confidence scores. Supports screenshots, scanned documents, photos of text. …
- `html_to_markdown` — Convert HTML documents to clean, structured markdown. Preserves headings, links, tables, lists. Perfect for agents that…
- `extract_tables` — Extract tables from any supported document format as structured JSON. Handles PDF tables, HTML tables, CSV-like structu…
- `summarize_document` — Parse any document and generate a structured summary with configurable detail level. Extracts key information, main poi…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get agenson-horrowitz/document-parser-mcp <tool-name>
```