Skip to main content
Glama
GongRzhe

Office Word MCP Server

add_footnote_before_text

Add footnotes before specific text in Word documents with proper superscript formatting to ensure correct display and citation placement.

Instructions

Add a footnote before specific text with proper superscript formatting. This enhanced function ensures footnotes display correctly as superscript.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filenameYes
search_textYes
footnote_textYes
output_filenameNo

Implementation Reference

  • MCP tool registration for 'add_footnote_before_text' which delegates execution to the handler in footnote_tools.py
    @mcp.tool()
    def add_footnote_before_text(filename: str, search_text: str, footnote_text: str, 
                                output_filename: str = None):
        """Add a footnote before specific text with proper superscript formatting.
        This enhanced function ensures footnotes display correctly as superscript."""
        return footnote_tools.add_footnote_before_text(filename, search_text, footnote_text, output_filename)
  • Primary handler logic: validates inputs, checks file accessibility, and invokes core robust footnote addition with position='before'
    async def add_footnote_before_text(filename: str, search_text: str, footnote_text: str, 
                                      output_filename: Optional[str] = None) -> str:
        """Add a footnote before specific text in a Word document with proper formatting.
        
        This enhanced function ensures proper superscript formatting by managing styles at the XML level.
        
        Args:
            filename: Path to the Word document
            search_text: Text to search for (footnote will be added before this text)
            footnote_text: Content of the footnote
            output_filename: Optional output filename (if None, modifies in place)
        """
        filename = ensure_docx_extension(filename)
        
        if not os.path.exists(filename):
            return f"Document {filename} does not exist"
        
        # Check if file is writeable
        is_writeable, error_message = check_file_writeable(filename)
        if not is_writeable:
            return f"Cannot modify document: {error_message}. Consider creating a copy first."
        
        try:
            # Use robust implementation
            success, message, details = add_footnote_robust(
                filename=filename,
                search_text=search_text,
                footnote_text=footnote_text,
                output_filename=output_filename,
                position="before",
                validate_location=True
            )
            return message
        except Exception as e:
            return f"Failed to add footnote: {str(e)}"
  • Core helper function performing low-level DOCX XML editing to insert proper Word footnote reference and content, supporting 'before'/'after' positions via direct elementtree manipulation and zip handling
    def add_footnote_robust(
        filename: str,
        search_text: Optional[str] = None,
        paragraph_index: Optional[int] = None,
        footnote_text: str = "",
        output_filename: Optional[str] = None,
        position: str = "after",
        validate_location: bool = True,
        auto_repair: bool = False
    ) -> Tuple[bool, str, Optional[Dict[str, Any]]]:
        """
        Add a footnote with robust validation and error handling.
        
        This is the main production-ready function with all fixes applied.
        """
        
        # Validate inputs
        if not search_text and paragraph_index is None:
            return False, "Must provide either search_text or paragraph_index", None
        
        if search_text and paragraph_index is not None:
            return False, "Cannot provide both search_text and paragraph_index", None
        
        if not os.path.exists(filename):
            return False, f"File not found: {filename}", None
        
        # Set working file
        working_file = output_filename if output_filename else filename
        if output_filename and filename != output_filename:
            import shutil
            shutil.copy2(filename, output_filename)
        
        try:
            # Read document parts
            doc_parts = {}
            with zipfile.ZipFile(filename, 'r') as zin:
                doc_parts['document'] = zin.read('word/document.xml')
                doc_parts['content_types'] = zin.read('[Content_Types].xml')
                doc_parts['document_rels'] = zin.read('word/_rels/document.xml.rels')
                
                # Read or create footnotes.xml
                if 'word/footnotes.xml' in zin.namelist():
                    doc_parts['footnotes'] = zin.read('word/footnotes.xml')
                else:
                    doc_parts['footnotes'] = _create_minimal_footnotes_xml()
                
                # Read styles
                if 'word/styles.xml' in zin.namelist():
                    doc_parts['styles'] = zin.read('word/styles.xml')
                else:
                    # Create minimal styles
                    doc_parts['styles'] = b'<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"/>'
            
            # Parse XML documents
            doc_root = etree.fromstring(doc_parts['document'])
            footnotes_root = etree.fromstring(doc_parts['footnotes'])
            styles_root = etree.fromstring(doc_parts['styles'])
            
            # Find target location
            nsmap = {'w': W_NS}
            
            if search_text:
                # Search for text in paragraphs
                found = False
                for para in doc_root.xpath('//w:p', namespaces=nsmap):
                    para_text = ''.join(para.xpath('.//w:t/text()', namespaces=nsmap))
                    if search_text in para_text:
                        target_para = para
                        found = True
                        break
                
                if not found:
                    return False, f"Text '{search_text}' not found in document", None
            else:
                # Use paragraph index
                paragraphs = doc_root.xpath('//w:p', namespaces=nsmap)
                if paragraph_index >= len(paragraphs):
                    return False, f"Paragraph index {paragraph_index} out of range", None
                target_para = paragraphs[paragraph_index]
            
            # Validate location if requested
            if validate_location:
                # Check if paragraph is in header/footer
                parent = target_para.getparent()
                while parent is not None:
                    if parent.tag in [f'{{{W_NS}}}hdr', f'{{{W_NS}}}ftr']:
                        return False, "Cannot add footnote in header/footer", None
                    parent = parent.getparent()
            
            # Get safe footnote ID
            footnote_id = _get_safe_footnote_id(footnotes_root)
            
            # Add footnote reference to document
            if position == "after":
                # Find last run in paragraph or create one
                runs = target_para.xpath('.//w:r', namespaces=nsmap)
                if runs:
                    last_run = runs[-1]
                    # Insert after last run
                    insert_pos = target_para.index(last_run) + 1
                else:
                    insert_pos = len(target_para)
            else:  # before
                # Find first run with text
                runs = target_para.xpath('.//w:r[w:t]', namespaces=nsmap)
                if runs:
                    first_run = runs[0]
                    insert_pos = target_para.index(first_run)
                else:
                    insert_pos = 0
            
            # Create footnote reference run
            ref_run = etree.Element(f'{{{W_NS}}}r')
            
            # Add run properties with superscript
            rPr = etree.SubElement(ref_run, f'{{{W_NS}}}rPr')
            rStyle = etree.SubElement(rPr, f'{{{W_NS}}}rStyle')
            rStyle.set(f'{{{W_NS}}}val', 'FootnoteReference')
            
            # Add footnote reference
            fn_ref = etree.SubElement(ref_run, f'{{{W_NS}}}footnoteReference')
            fn_ref.set(f'{{{W_NS}}}id', str(footnote_id))
            
            # Insert the reference run
            target_para.insert(insert_pos, ref_run)
            
            # Add footnote content
            new_footnote = etree.Element(f'{{{W_NS}}}footnote',
                attrib={f'{{{W_NS}}}id': str(footnote_id)}
            )
            
            # Add paragraph to footnote
            fn_para = etree.SubElement(new_footnote, f'{{{W_NS}}}p')
            
            # Add paragraph properties
            pPr = etree.SubElement(fn_para, f'{{{W_NS}}}pPr')
            pStyle = etree.SubElement(pPr, f'{{{W_NS}}}pStyle')
            pStyle.set(f'{{{W_NS}}}val', 'FootnoteText')
            
            # Add the footnote reference marker
            marker_run = etree.SubElement(fn_para, f'{{{W_NS}}}r')
            marker_rPr = etree.SubElement(marker_run, f'{{{W_NS}}}rPr')
            marker_rStyle = etree.SubElement(marker_rPr, f'{{{W_NS}}}rStyle')
            marker_rStyle.set(f'{{{W_NS}}}val', 'FootnoteReference')
            marker_ref = etree.SubElement(marker_run, f'{{{W_NS}}}footnoteRef')
            
            # Add space after marker
            space_run = etree.SubElement(fn_para, f'{{{W_NS}}}r')
            space_text = etree.SubElement(space_run, f'{{{W_NS}}}t')
            space_text.set(f'{{{XML_NS}}}space', 'preserve')
            space_text.text = ' '
            
            # Add footnote text
            text_run = etree.SubElement(fn_para, f'{{{W_NS}}}r')
            text_elem = etree.SubElement(text_run, f'{{{W_NS}}}t')
            text_elem.text = footnote_text
            
            # Append footnote to footnotes.xml
            footnotes_root.append(new_footnote)
            
            # Ensure styles exist
            _ensure_footnote_styles(styles_root)
            
            # Ensure coherence
            content_types_xml = _ensure_content_types(doc_parts['content_types'])
            document_rels_xml = _ensure_document_rels(doc_parts['document_rels'])
            
            # Write modified document
            temp_file = working_file + '.tmp'
            with zipfile.ZipFile(temp_file, 'w', zipfile.ZIP_DEFLATED) as zout:
                with zipfile.ZipFile(filename, 'r') as zin:
                    # Copy unchanged files
                    for item in zin.infolist():
                        if item.filename not in [
                            'word/document.xml', 'word/footnotes.xml', 'word/styles.xml',
                            '[Content_Types].xml', 'word/_rels/document.xml.rels'
                        ]:
                            zout.writestr(item, zin.read(item.filename))
                
                # Write modified files
                zout.writestr('word/document.xml',
                    etree.tostring(doc_root, encoding='UTF-8', xml_declaration=True, standalone="yes"))
                zout.writestr('word/footnotes.xml',
                    etree.tostring(footnotes_root, encoding='UTF-8', xml_declaration=True, standalone="yes"))
                zout.writestr('word/styles.xml',
                    etree.tostring(styles_root, encoding='UTF-8', xml_declaration=True, standalone="yes"))
                zout.writestr('[Content_Types].xml', content_types_xml)
                zout.writestr('word/_rels/document.xml.rels', document_rels_xml)
            
            # Replace original with temp file
            os.replace(temp_file, working_file)
            
            details = {
                'footnote_id': footnote_id,
                'location': 'search_text' if search_text else 'paragraph_index',
                'styles_created': ['FootnoteReference', 'FootnoteText'],
                'coherence_verified': True
            }
            
            return True, f"Successfully added footnote (ID: {footnote_id}) to {working_file}", details
            
        except Exception as e:
            # Clean up temp file if exists
            temp_file = working_file + '.tmp'
            if os.path.exists(temp_file):
                os.remove(temp_file)
            return False, f"Error adding footnote: {str(e)}", None
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'proper superscript formatting' and 'ensures footnotes display correctly,' which hints at formatting behavior, but lacks critical details: whether this modifies files in-place, requires specific permissions, handles errors, or affects document structure. For a mutation tool with zero annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief (two sentences) and front-loaded with the core purpose. However, the second sentence ('This enhanced function ensures...') is somewhat redundant and doesn't add substantial value, slightly reducing efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (modifying documents with footnotes), lack of annotations, 0% schema coverage, no output schema, and multiple sibling tools, the description is incomplete. It misses parameter explanations, behavioral details, and differentiation from alternatives, leaving significant gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It doesn't explain any of the 4 parameters (filename, search_text, footnote_text, output_filename). For example, it doesn't clarify what 'search_text' targets or how 'output_filename' works. The description adds no parameter meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Add a footnote before specific text with proper superscript formatting.' This specifies the verb (add), resource (footnote), and location (before specific text). However, it doesn't explicitly differentiate from sibling tools like 'add_footnote_after_text' or 'add_footnote_enhanced,' which would require a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With multiple sibling tools for footnotes (e.g., 'add_footnote_after_text,' 'add_footnote_enhanced'), there's no indication of context, prerequisites, or exclusions. The second sentence about 'enhanced function' is vague and doesn't clarify usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/GongRzhe/Office-Word-MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server