onit-office

onit-office

MCP server for creating and editing PowerPoint, Excel, and Word documents. Runs as an SSE server and provides 18 tools for document manipulation.

Category
Visit Server

README

onit-office

Standalone MCP server for Microsoft Office document creation (PowerPoint, Excel, Word). Runs as an SSE server that can be used with any MCP client.

Vendored from onit.

Installation

pip install onit-office

Usage

Start the server (runs in background):

onit-office
# or
onit-office start

Start in foreground (for debugging):

onit-office start --foreground

Custom host/port:

onit-office start --host 127.0.0.1 --port 8000

Check status:

onit-office status

Stop the server:

onit-office stop

Using with onit

onit can connect to onit-office as an MCP SSE server. Start onit-office first, then launch onit with the --mcp-sse flag:

onit-office start
onit --mcp-sse http://localhost:18203/sse --web

This gives onit access to all 18 office document tools through its web interface.

MCP Client Configuration

Once running, connect any MCP client to the SSE endpoint:

http://localhost:18203/sse

Example MCP client config:

{
  "mcpServers": {
    "onit-office": {
      "url": "http://localhost:18203/sse"
    }
  }
}

Tools

18 tools for creating and editing Office documents:

PowerPoint (9 tools):

  • create_presentation - Create a new 16:9 presentation with title slide
  • add_slide - Add slides with various layouts (text, bullets, images, two-column)
  • add_table_slide - Add data tables with formatted headers
  • add_images_slide - Display multiple images in grid layouts
  • style_slide - Apply background colors and styling
  • get_presentation_info - Inspect presentation structure
  • read_presentation - Read full text content from all slides
  • modify_presentation - Edit text in shapes or delete slides
  • download_media - Download media files from URLs

Excel (4 tools):

  • create_excel - Create Excel files with headers and data
  • add_excel_rows - Append rows to existing Excel files
  • read_excel - Read cell contents from existing Excel files
  • modify_excel_cells - Edit specific cells in existing Excel files

Word (4 tools):

  • create_document - Create Word documents with optional headers/logos
  • add_document_content - Add headings, paragraphs, bullets, images, tables
  • read_document - Read full content from existing Word documents
  • modify_document - Edit or delete paragraphs in existing Word documents

General (1 tool):

  • get_file - Retrieve a created file as base64-encoded data for download

Data Directory

By default, created files are stored in a temporary directory unique to each server process (<system temp dir>/onit-office-<pid>, e.g. /tmp/onit-office-12345). This directory is automatically cleaned up when the server exits.

To persist files across restarts, specify a custom data path:

onit-office start --data-path /path/to/my/data

When --data-path is provided, auto-cleanup is disabled and files are retained.

Docker

See docs/DOCKER.md for Docker build and run instructions.

Testing

See docs/TESTING.md for how to run and structure tests.

License

Apache 2.0

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured