Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Microsoft Office

БесплатноНе проверен

Enables creating PowerPoint presentations with ERD diagrams from text prompts by connecting to Microsoft Visio/PowerPoint tools via an MCP server.

GitHubEmbed

Описание

Enables creating PowerPoint presentations with ERD diagrams from text prompts by connecting to Microsoft Visio/PowerPoint tools via an MCP server.

README

This project uses LangChain's MultiServerMCPClient to connect to a custom MCP server (Microsoft Office/Visio MCP) and generate a PowerPoint presentation containing an ERD (Entity-Relationship Diagram) visualization.

Prerequisites

  • Python 3.8+
  • Microsoft Office (PowerPoint/Visio) installed
  • MCP Server running with Visio/PowerPoint tools

Installation

  1. Clone the repository:

    git clone <repository-url>
    cd microsoft-office-mcp
    
  2. Install dependencies:

    pip install -r requirements.txt
    

Usage

Start MCP Server

Run the MCP server that exposes Visio/PowerPoint tools:

python server.py

Run the Agent

Execute the agent script with a prompt describing the desired ERD:

python agent.py

Modify the main() function in agent.py to customize the prompt:

async def main():
    agent = ERDAgent()
    prompt = """
    Create a PowerPoint presentation with an ERD diagram for this scenario:
    
    [Your ERD description here]
    
    Key requirements:
    - Use Crow's Foot notation for relationships
    - Keep entities within slide boundaries
    - Save as vsdx file
    """
    await agent.run(prompt)

How It Works

  1. server.py: Implements a FastMCP server that exposes:

    • init_new_visio_document: Creates a new Visio/PowerPoint document
    • draw_erd_entity: Draws ERD entity shapes with specified coordinates
    • connect_entities: Creates relationship connectors between entities
    • save_as_vsdx: Saves the diagram as a .vsdx file
  2. agent.py: A LangGraph agent that:

    • Connects to the MCP server using MultiServerMCPClient
    • Uses create_react_agent with Ollama (or another LLM) for reasoning
    • Executes the MCP tools sequentially to build the diagram
    • Streams the agent's thought process to the console

Customization

  • LLM Model: Change OLLAMA_MODEL in .env or config.py
  • MCP Server URL: Update MCP_SERVER_URL in .env
  • Diagram Design: Modify the prompt in agent.py to change:
    • Entities and attributes
    • Relationships and cardinality
    • Document layout and styling

Example Prompt

"""
Design a simple ERD diagram for a gym membership system.

Entities:
- MEMBERS (member_id, name, email, phone, address)
- CLASSES (class_id, name, capacity, instructor)
- MEMBERSHIPS (membership_id, type, start_date, end_date)

Relationships:
- A MEMBER can have one MEMBERSHIP (1:1)
- A MEMBER can attend multiple CLASSES (M:N)
- A CLASS has one instructor (1:1)

Requirements:
- Use Crow's Foot notation
- Keep the diagram clean and organized
- Save as vsdx file with appropriate filename
"""

from github.com/jacobNar/microsoft-office-mcp

Установка Microsoft Office

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/jacobNar/microsoft-office-mcp

FAQ

Microsoft Office MCP бесплатный?

Да, Microsoft Office MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Microsoft Office?

Нет, Microsoft Office работает без API-ключей и переменных окружения.

Microsoft Office — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Microsoft Office в Claude Desktop, Claude Code или Cursor?

Открой Microsoft Office на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Microsoft Office with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории development