get_document
Retrieve and validate Markdown document content and structure from a specified file path to enable editing operations.
Instructions
Get the complete document content and structure.
Args:
document_path: Path to the Markdown file
validation_level: Validation strictness - "STRICT", "NORMAL", or "PERMISSIVE"
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| document_path | Yes | ||
| validation_level | No | NORMAL |
Implementation Reference
- Primary handler for the 'get_document' tool, decorated with @mcp.tool() for registration. Loads document content and structure using StatelessMarkdownProcessor and returns full markdown content, section list, and metadata.@self.mcp.tool() def get_document(document_path: str, validation_level: str = "NORMAL") -> Dict[str, Any]: """ Get the complete document content and structure. Args: document_path: Path to the Markdown file validation_level: Validation strictness - "STRICT", "NORMAL", or "PERMISSIVE" """ try: validation_map = {"STRICT": ValidationLevel.STRICT, "NORMAL": ValidationLevel.NORMAL, "PERMISSIVE": ValidationLevel.PERMISSIVE} validation_enum = validation_map.get(validation_level.upper(), ValidationLevel.NORMAL) editor = self.processor.load_document(document_path, validation_enum) sections = editor.get_sections() content = editor.to_markdown() return { "success": True, "document_path": document_path, "content": content, "sections": [ { "id": section.id, "title": section.title, "level": section.level, "line_start": section.line_start, "line_end": section.line_end } for section in sections ], "metadata": { "total_sections": len(sections), "total_lines": len(content.split('\n')), "file_size": len(content), "validation_level": validation_level } } except Exception as e: return self.processor.create_error_response(str(e), type(e).__name__)
- Internal helper implementation for 'get_document' used in synchronous tool calls via call_tool_sync. Similar logic to main handler but wrapped in execute_operation.def _get_document_impl(self, document_path: str) -> Dict[str, Any]: """Implementation for get_document tool.""" def operation(editor): from .safe_editor_types import EditResult, EditOperation content = editor.to_markdown() sections = editor.get_sections() document_data = { "content": content, "sections": [ { "id": section.id, "title": section.title, "level": section.level, "start_line": section.line_start, "end_line": section.line_end } for section in sections ], "word_count": len(content.split()), "character_count": len(content) } return EditResult( success=True, operation=EditOperation.BATCH_OPERATIONS, modified_sections=[], errors=[], warnings=[], metadata=document_data ) return self.processor.execute_operation(document_path, operation, auto_save=False)
- Alternative handler for 'get_document' in the enhanced MCP server subclass, providing document content and statistics.@self.mcp.tool() def get_document(document_path: str, validation_level: str = "NORMAL") -> Dict[str, Any]: """Get the complete document (stateless only).""" try: validation_map = {"STRICT": ValidationLevel.STRICT, "NORMAL": ValidationLevel.NORMAL, "PERMISSIVE": ValidationLevel.PERMISSIVE} validation_enum = validation_map.get(validation_level.upper(), ValidationLevel.NORMAL) editor = self.processor.load_document(document_path, validation_enum) content = editor.to_markdown() statistics = editor.get_statistics() return { "success": True, "document": content, "statistics": { "total_sections": statistics.total_sections, "total_lines": statistics.total_lines, "word_count": statistics.word_count, "character_count": statistics.character_count }, "document_path": document_path, "stateless": True } except Exception as e: return self.processor.create_error_response(str(e), type(e).__name__)