mcp-office-parser
Allows reading, writing, and converting LibreOffice documents (ODT, ODS, ODP) as well as Microsoft Office formats (DOCX, XLSX, PPTX) and PDF.
Provides tools to read spreadsheet data as 2D arrays, create new spreadsheets, and convert between ODS, XLSX, CSV formats.
Supports reading presentations from ODP and PPTX files, with text extraction and conversion capabilities.
Enables reading, writing, and converting Writer documents (ODT, DOCX) including text extraction, editing, and creation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-office-parser convert my report.docx to PDF"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-office-parser
⚠️ AI-Generated Project — Use With Caution
This project was generated with the assistance of AI. While efforts have been made to verify correctness, the code may contain errors, security vulnerabilities, or unexpected behavior. It has not been fully audited or tested in production environments. Use at your own risk, and always review the source code before deploying.
An MCP (Model Context Protocol) server for reading, writing, and converting LibreOffice and Microsoft Office documents — implemented in pure JavaScript with no external binary dependencies.
Quick Start
npx @barry.wu0329/mcp-office-parserRelated MCP server: Office-MCP-Server
What It Does
mcp-office-parser exposes document manipulation capabilities as MCP tools that AI assistants (like Claude) can use to:
Read ODT, DOCX, ODP, PPTX, TXT, and more
Read spreadsheets from ODS, XLSX, CSV files
Create new documents (ODT, ODS, DOCX, XLSX, PDF)
Edit existing documents by inserting text
Convert between formats (e.g., DOCX → PDF, ODT → TXT)
Search through documents for specific content
Merge multiple documents into one
Configuration
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-office-parser": {
"command": "npx",
"args": ["@barry.wu0329/mcp-office-parser"]
}
}
}VS Code (MCP extension)
Add to .vscode/mcp.json:
{
"servers": {
"mcp-office-parser": {
"command": "npx",
"args": ["@barry.wu0329/mcp-office-parser"]
}
}
}Supported File Formats
Format | Read | Write | Notes |
| ✅ | ✅ | LibreOffice Writer |
| ✅ | ✅ | LibreOffice Calc |
| ✅ | ✅ | LibreOffice Impress |
| ✅ | ✅ | Microsoft Word |
| ✅ | ✅ | Microsoft Excel |
| ✅ | — | Microsoft PowerPoint |
| ✅ | ✅ | Plain text |
| ✅ | ✅ | Comma-separated values |
| ✅ | ✅ | Read via pdf-parse; write via pdf-lib |
| — | ✅ | HTML conversion output |
Available MCP Tools
Tool | Description |
| Get file metadata (size, format, modified time) |
| Extract plain text from a document |
| Read spreadsheet data as a 2D array |
| Create a new document with content |
| Insert text at start, end, or replace content |
| Find all supported documents in a directory |
| Search document contents for a query string |
| Word count, character count, sentence count, etc. |
| Convert between formats |
| Merge multiple documents into one |
MCP Resources
documents://— Lists all discoverable documents as JSONdocument://{path}— Reads a document's text content
Requirements
Node.js >= 18.17.0
No LibreOffice or other external tools needed
License
MIT
Available Tools
11 toolsconvert_documentD
Inputs: source_path (required), target_path (required), target_format (required).
create_documentD
Inputs: path (required), doc_type (required), content.
get_document_infoD
Inputs: path (required).
get_document_statisticsD
Inputs: path (required).
insert_table_docxD
Inputs: path (required), rows (required), position.
insert_text_at_positionD
Inputs: path (required), text (required), position.
list_documentsD
Inputs: search_path.
merge_text_documentsD
Inputs: output_path (required), document_paths (required), separator.
read_document_textD
Inputs: path (required).
read_spreadsheet_dataD
Inputs: path (required), max_rows, sheet_name.
search_documentsD
Inputs: query (required), search_path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Most tools have distinct targets (e.g., read_document_text vs. read_spreadsheet_data), but get_document_info and get_document_statistics could be confused, and insert_text_at_position and insert_table_docx are both insertion operations with unclear boundaries. Without descriptions, an agent might struggle to pick the right tool for metadata vs. statistics.
All tools follow a verb_noun pattern (get, read, create, insert, list, search, convert, merge), which is consistent. Minor deviations include mixing 'read' and 'get' for similar actions, and suffixes like 'at_position' vs. 'docx' are not uniform, but the overall pattern is readable.
11 tools is within the ideal 3-15 range and each tool seems to serve a distinct function in document processing. The count feels well-scoped and not bloated.
The surface covers reading, creating, inserting, converting, and merging documents, but lacks obvious operations like deleting or updating documents, and spreadsheet write capabilities are absent. This may force an agent to work around missing functionality for typical office document workflows.
Maintenance
Related MCP Connectors
Parse, convert and create Office and PDF documents. OAuth at /mcp/connect/, API key at /mcp/.
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
Generate, edit, merge, translate and PDF-convert PowerPoint (.pptx) over MCP. 8 tools.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for reading, writing, editing, formatting, and exporting Microsoft Office documents (Word, Excel, PowerPoint) via stdio JSON-RPC, with 47 tools and cross-platform support.473MIT
- AlicenseBqualityCmaintenanceProvides MCP tools for working with Microsoft Word documents, enabling reading, editing with tracked changes, formatting, table manipulation, comments, and PDF conversion via direct OOXML manipulation.37MIT
- AlicenseCqualityDmaintenanceEnables comprehensive DOCX/OOXML document manipulation via MCP, covering text, tables, images, content controls, comments, tracked changes, and metadata.3447 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables creating, reading, editing, and verifying PDF, Word, Excel, and PowerPoint documents through MCP tools that return structured results. It preserves source files by default for edits and supports local stdio operation without network requests.MIT