MCP Server Office
@famano
About MCP Server Office
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"test": {
"command": "docker"
}
}
}Tools
7`path` (string) - Absolute path to the target file
Images are converted to [Image] placeholders, and track changes are not shown
`path` (string) - Absolute path to target file
Use double line breaks for new paragraphs, and [Table] tag with | separators for tables
`path` (string) - Absolute path to file to edit
Each search string must match exactly once within the specified paragraph
`path` (string) - Absolute path to file to edit
Overview
What is MCP Server Office?
MCP Server Office is a Model Context Protocol (MCP) server that provides tools to read and write Microsoft Word (.docx) files. It is intended for developers who need to programmatically interact with Word documents through MCP-compatible clients like Claude Desktop.
How to use MCP Server Office?
Install via pip (pip install mcp-server-office) or uv (uvx mcp-server-office), then start the server with mcp-server-office. Alternatively, install automatically for Claude Desktop using Smithery. The server exposes four tools: read_docx, write_docx, edit_docx_paragraph, and edit_docx_insert.
Key features of MCP Server Office
- Read complete docx contents including tables and images
- Create new docx files with specified content
- Edit specific paragraphs via search-and-replace
- Insert new paragraphs at chosen positions
Use cases of MCP Server Office
- Programmatically extract text and tables from Word documents
- Generate .docx reports or documents from AI-driven workflows
- Automate minor edits to existing Word files (e.g., updating boilerplate text)
- Insert additional content into a document without overwriting the whole file
FAQ from MCP Server Office
What image handling does read_docx have?
Images are converted to [Image] placeholders in the output. Track changes are not shown.
How do I write tables with write_docx?
Use the [Table] tag with pipe (|) separators to define table rows and columns.
Can I edit a paragraph that contains the search text multiple times?
No. Each search string must match exactly once within the specified paragraph for edit_docx_paragraph to succeed.
What are the runtime requirements?
Python 3.12 or higher, plus the mcp[cli] >= 1.2.0 and python-docx >= 1.1.2 packages.
Where are the Word files stored?
The server operates on local file paths provided by the user; it does not manage cloud storage or remote file systems.
Frequently asked questions
What image handling does `read_docx` have?
Images are converted to `[Image]` placeholders in the output. Track changes are not shown.
How do I write tables with `write_docx`?
Use the `[Table]` tag with pipe (`|`) separators to define table rows and columns.
Can I edit a paragraph that contains the search text multiple times?
No. Each `search` string must match exactly once within the specified paragraph for `edit_docx_paragraph` to succeed.
What are the runtime requirements?
Python 3.12 or higher, plus the `mcp[cli] >= 1.2.0` and `python-docx >= 1.1.2` packages.
Where are the Word files stored?
The server operates on local file paths provided by the user; it does not manage cloud storage or remote file systems.
Basic information
More Other MCP servers
IDA Pro MCP
mrexodiaAI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Inbox Zero AI MCP
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Comments