mcp-document-converter

flowchart TB
    subgraph Parsers["Parsers"]
        MD[Markdown]
        DOCX1[DOCX]
        HTML1[HTML]
        PDF1[PDF]
        TXT1[Text]
    end

    subgraph IR["Intermediate Representation (IR)"]
        DT[Document Tree]
        META[Metadata]
        ASSETS[Assets]
    end

    subgraph Renderers["Renderers"]
        HTML2[HTML]
        PDF2[PDF]
        MD2[Markdown]
        DOCX2[DOCX]
        TXT2[Text]
    end

    MD --> IR
    DOCX1 --> IR
    HTML1 --> IR
    PDF1 --> IR
    TXT1 --> IR
    
    IR --> HTML2
    IR --> PDF2
    IR --> MD2
    IR --> DOCX2
    IR --> TXT2

flowchart LR
    subgraph Sources["Source Formats"]
        MD_S[Markdown]
        HTML_S[HTML]
        DOCX_S[DOCX]
        PDF_S[PDF]
        TXT_S[Text]
    end

    subgraph Targets["Target Formats"]
        MD_T[Markdown]
        HTML_T[HTML]
        DOCX_T[DOCX]
        PDF_T[PDF]
        TXT_T[Text]
    end

    MD_S --> Targets
    HTML_S --> Targets
    DOCX_S --> Targets
    PDF_S --> Targets
    TXT_S --> Targets

pip install mcp-document-converter

git clone https://github.com/xt765/mcp-document-converter.git
cd mcp-document-converter
pip install -e .

{
  "mcpServers": {
    "mcp-document-converter": {
      "command": "uvx",
      "args": [
        "mcp-document-converter"
      ]
    }
  }
}

{
  "mcpServers": {
    "mcp-document-converter": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/xt765/mcp-document-converter",
        "mcp-document-converter"
      ]
    }
  }
}

{
  "mcpServers": {
    "mcp-document-converter": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://gitee.com/xt765/mcp-document-converter",
        "mcp-document-converter"
      ]
    }
  }
}

pip install mcp-document-converter

{
  "mcpServers": {
    "mcp-document-converter": {
      "command": "mcp-document-converter",
      "args": []
    }
  }
}

# Markdown to HTML
convert_document(
    source_path="document.md",
    target_format="html"
)

# HTML to PDF
convert_document(
    source_path="document.html",
    target_format="pdf"
)

# DOCX to Markdown
convert_document(
    source_path="document.docx",
    target_format="markdown"
)

# Conversion with options
convert_document(
    source_path="document.md",
    target_format="html",
    output_path="output.html",
    options={
        "css": "custom.css",
        "preserve_metadata": True
    }
)

list_supported_formats()

get_conversion_matrix()

can_convert(source_format="markdown", target_format="pdf")

get_format_info(format="markdown")

from mcp_document_converter import DocumentConverter
from mcp_document_converter.registry import get_registry
from mcp_document_converter.parsers import MarkdownParser, HTMLParser
from mcp_document_converter.renderers import HTMLRenderer, PDFRenderer

# Register parsers and renderers
registry = get_registry()
registry.register_parser(MarkdownParser())
registry.register_parser(HTMLParser())
registry.register_renderer(HTMLRenderer())
registry.register_renderer(PDFRenderer())

# Create converter
converter = DocumentConverter(registry)

# Convert document
result = converter.convert(
    source="input.md",
    target_format="html",
    output_path="output.html"
)

if result.success:
    print(f"✅ Conversion successful: {result.output_path}")
else:
    print(f"❌ Conversion failed: {result.error_message}")

{
  "source_path": "/path/to/document.md",
  "target_format": "html",
  "output_path": "/path/to/output.html",
  "options": {
    "css": "body { font-family: Arial; }",
    "preserve_metadata": true
  }
}

from typing import List, Union
from pathlib import Path
from mcp_document_converter.core.parser import BaseParser
from mcp_document_converter.core.ir import DocumentIR, Node, NodeType

class MyParser(BaseParser):
    @property
    def supported_extensions(self) -> List[str]:
        return [".myext"]
    
    @property
    def format_name(self) -> str:
        return "myformat"
    
    @property
    def mime_types(self) -> List[str]:
        return ["application/x-myformat"]
    
    def parse(self, source: Union[str, Path, bytes], **options) -> DocumentIR:
        # Read source file
        content = self._read_source(source)
        
        # Parse into DocumentIR
        document = DocumentIR()
        document.title = "My Document"
        
        # Add content nodes
        document.add_node(Node(
            type=NodeType.PARAGRAPH,
            content=[Node(type=NodeType.TEXT, content="Hello World")]
        ))
        
        return document

from typing import Any
from mcp_document_converter.core.renderer import BaseRenderer
from mcp_document_converter.core.ir import DocumentIR

class MyRenderer(BaseRenderer):
    @property
    def output_extension(self) -> str:
        return ".myext"
    
    @property
    def format_name(self) -> str:
        return "myformat"
    
    @property
    def mime_type(self) -> str:
        return "application/x-myformat"
    
    def render(self, document: DocumentIR, **options: Any) -> str:
        # Render DocumentIR to target format
        parts = []
        
        if document.title:
            parts.append(f"# {document.title}")
        
        for node in document.content:
            # Render each node
            pass
        
        return "\n".join(parts)

from mcp_document_converter.registry import get_registry

# Register new parser and renderer
registry = get_registry()
registry.register_parser(MyParser())
registry.register_renderer(MyRenderer())

# Run all tests
python tests/test_conversion.py

# Run specific test
python tests/test_conversion.py::test_markdown_to_html