Powerpoint Automation MCP 伺服器 | PlugMCP
跳到正文 MCP server for PowerPoint
把任意工具接入任意代理。面向非開發者的 MCP 伺服器目錄;閘道承載流量,n8n 承載應用。
產品
目錄
開發者
公司
Features
Presentation Management : Create, open, save, and close presentations
Slide Operations : Add, delete, and manage slides with various layouts
Content Creation : Add text boxes, images, tables, and charts
Text Formatting : Update text with font styling (name, size, bold, italic)
Shape Manipulation : Move, resize, and modify shape properties
Table Operations : Create tables and update cell content
Chart Creation : Add various chart types (column, line, pie, bar) with data
Group Management : Ungroup shapes for easier manipulation
Layout Support : Work with different slide layouts and placeholders
Recommended Prompts
Translation Scenario For translating presentations, process in batches to avoid context overflow and ensure data safety:
Translate this presentation [absolute path of ppt], processing 10 slides at a time and saving after each batch of 10 slides.
Prevents token limit issues on large presentations
Saves progress incrementally to avoid data loss
Allows for review between batches
Installation git clone https://github.com/buckylee2019/powerpoint-automation-mcp.git
cd powerpoint-automation-mcp
uv sync
Running the Server uv run --directory /path/to/powerpoint-automation-mcp mcp-ppt-server
API Reference The server provides 25+ tools for comprehensive PowerPoint automation. All operations work with a single active presentation to simplify the API.
Presentation Management
initialize_powerpoint() -> boolInitialize the PowerPoint automation system.
create_presentation(template: str = None) -> DictCreate a new presentation, optionally from a template.
template: Optional path to template file
open_presentation(file_path: str) -> DictOpen an existing PowerPoint file.
file_path: Full path to .pptx file
get_presentation() -> DictGet information about the currently active presentation.
save_presentation(path: str = None) -> DictSave the active presentation.
path: Optional save path (uses current path if omitted)
close_presentation() -> DictClose the active presentation.
Slide Management
get_slides() -> List[Dict]Get list of all slides with metadata.
add_slide(layout_index: int = 1) -> DictAdd a new slide with specified layout.
layout_index: Layout type (0=Title, 1=Title+Content, etc.)
delete_slide(slide_index: int) -> DictDelete a slide from the presentation.
slide_index: 0-based slide index
get_slide_layouts() -> DictGet all available slide layouts with their properties.
set_slide_title(slide_index: int, title: str) -> DictSet the title of a slide.
Content Inspection
get_slide_shapes(slide_index: int) -> DictALWAYS RUN FIRST! Get all shapes in a slide with properties and IDs.
Returns shape types, positions, sizes, and text content
Identifies grouped shapes that may need ungrouping
get_slide_text(slide_index: int) -> DictGet all text content in a slide organized by shape.
Detects grouped shapes that may need ungrouping first
Text and Shape Manipulation
update_text(slide_index: int, shape_index: int, text: str, font_name: str = None, font_size: int = None, bold: bool = None, italic: bool = None, preserve_existing: bool = True) -> DictUpdate text content with optional formatting.
Supports font styling while preserving existing formatting
preserve_existing: Keep original formatting for unspecified properties
update_shape_by_id(slide_index: int, shape_id: str, text: str = None, left: float = None, top: float = None, width: float = None, height: float = None) -> DictUpdate shape properties by ID.
Positions and sizes in inches
Content Creation
add_textbox(slide_index: int, text: str, left: float = 1, top: float = 1, width: float = 4, height: float = 2) -> DictAdd a text box to a slide.
add_image(slide_index: int, image_path: str, left: float = 1, top: float = 1, width: float = None, height: float = None) -> Dict
Maintains aspect ratio if only width or height specified
add_table(slide_index: int, rows: int, cols: int, left: float = 1, top: float = 1, width: float = 8, height: float = 4) -> Dict
add_chart(slide_index: int, chart_type: str, categories: List[str], series_names: List[str], series_values: List[List[float]], left: float = 1, top: float = 1, width: float = 8, height: float = 4, has_legend: bool = True) -> DictAdd a chart with multiple data series.
chart_type: 'COLUMN', 'LINE', 'PIE', 'BAR'
categories: X-axis labels
series_names: Legend labels
series_values: Data values for each series
Table Operations
update_table_cell(slide_index: int, shape_index: int, row: int, col: int, text: str) -> DictUpdate text in a specific table cell.
get_table_content(slide_index: int, shape_index: int) -> DictRetrieve all content from a table.
Advanced Operations
ungroup_shapes(slide_index: int) -> DictUngroup all text-containing groups in a slide.
Only processes simple groups (no nested groups)
Preserves shape positions and properties
Skips groups without text content
Usage Workflow
Initialize : Call initialize_powerpoint()
Open/Create : Use open_presentation() or create_presentation()
Inspect : Always run get_slide_shapes() first to understand slide structure
Ungroup if needed : Use ungroup_shapes() if grouped shapes are detected
Modify : Use appropriate tools to add/modify content
Save : Call save_presentation() to persist changes
Error Handling All functions return dictionaries with either success data or error information:
// Success response
{
"success": true,
"message": "Operation completed",
"data": {...}
}
// Error response
{
"error": "Description of what went wrong"
}
MCP Configuration Add to your MCP settings:
{
"mcpServers": {
"powerpoint-automation": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/powerpoint-automation-mcp",
"mcp-ppt-server"
]
}
}
}
Dependencies
python-pptx: PowerPoint file manipulation
mcp: Model Context Protocol framework
fastmcp: Simplified MCP server creation
License MIT License - see LICENSE file for details.
N8n Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. Filesystem Read, write, search and move files in the directories you allow. The reference filesystem server from the Model Context Protocol project. Sequential Thinking Step-by-step problem solving for agents: break a problem into thoughts, revise them and branch. The reference server from the Model Context Protocol project. Time The current time in any timezone and conversions between timezones. The reference server from the Model Context Protocol project. MinerU Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. Paper Search Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, and IACR. Fetch PDFs and extract full text to accelerate literature reviews. Get consistent Google Sheets Search and inspect Google Sheets, create and edit spreadsheets, scan for data issues, review edit history, and manage comments. Obsidian Skills Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas. OfficeCLI OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation requir Gpt Researcher An autonomous agent that conducts deep research on any data using any LLM providers Activepieces AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents N8n MCP server that lets Claude, ChatGPT, Cursor and other AI assistants operate n8n: debug, edit, validate, test and build workflows on any n8n instance Productivity MCP 伺服器 最佳 Productivity MCP 伺服器 canvas-design Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create ori xlsx Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
如何安裝 Powerpoint Automation? 在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
Powerpoint Automation 需要 API 金鑰嗎? 這筆記錄未列出必要的環境變數。
Powerpoint Automation 使用哪種傳輸方式? Powerpoint Automation 透過 stdio 在本機執行。
Powerpoint Automation 上次檢查是什麼時候? 上次檢查時間:2026-11-05。 MCP server for PowerPoint
工具
0 / 10