powerpoint-mcp-live
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_open_presentationsA | List all presentations currently open in PowerPoint. Returns: JSON with each presentation's name, full path, save state, slide count, and whether it's the active presentation. |
| get_presentation_infoA | Get slide count, per-slide titles, and the active slide for an open presentation. Args: presentation: Presentation name or path (None = active presentation). Returns: JSON with each slide's index, title text (if it has a title placeholder), and layout. |
| save_presentationA | Save an open presentation in place (equivalent to pressing Ctrl+S). Args: presentation: Presentation name or path (None = active presentation). Returns: JSON confirmation. |
| list_slidesA | List slides in an open presentation, with index and title text. Args: presentation: Presentation name or path (None = active presentation). Returns: JSON with each slide's index and title (if it has one). |
| add_slideA | Add a new slide to an open presentation. Args: presentation: Presentation name or path (None = active presentation). index: 1-based position to insert at (None = append at the end). layout: One of "title", "text", "two_content", "title_only", "blank" (default: "text"). Returns: JSON with the new slide's index. |
| delete_slideA | Delete a slide from an open presentation. Args: presentation: Presentation name or path (None = active presentation). index: 1-based slide index (required). Returns: JSON confirmation. |
| duplicate_slideA | Duplicate a slide, inserting the copy immediately after the original. Args: presentation: Presentation name or path (None = active presentation). index: 1-based slide index to duplicate (required). Returns: JSON with the new slide's index. |
| move_slideB | Move a slide to a new position in the slide order. Args: presentation: Presentation name or path (None = active presentation). index: Current 1-based slide index (required). new_index: Target 1-based position (required). Returns: JSON confirmation. |
| activate_slideA | Make a slide the visible slide in PowerPoint's active window. Args: presentation: Presentation name or path (None = active presentation). index: 1-based slide index (required). Returns: JSON confirmation. |
| list_shapesA | List shapes on a slide with name, type, position, and text (if any). Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). Returns: JSON with each shape's 1-based index, name, MsoShapeType, position/ size (points), and text. |
| get_slide_textA | Read all text on a slide — the title plus every other text-bearing shape. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). Returns: JSON with the title and a list of body text strings, in shape order. |
| add_textboxA | Add a text box to a slide. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). text: Text content. left, top, width, height: Position and size in points. Returns: JSON with the new shape's name and 1-based index on the slide. |
| set_shape_textB | Set the text of an existing shape (title, placeholder, or text box). Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). shape: Shape name, or its 1-based index on the slide (required). text: New text content. Returns: JSON confirmation. |
| delete_shapeA | Delete a shape from a slide. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). shape: Shape name, or its 1-based index on the slide (required). Returns: JSON confirmation. |
| set_shape_positionA | Move and/or resize a shape. Only provided arguments are changed. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). shape: Shape name, or its 1-based index on the slide (required). left, top, width, height: New position/size in points (None = unchanged). Returns: JSON with the shape's resulting position and size. |
| format_shape_textA | Format the text of a shape (font style, name, size, color). Only arguments that are explicitly set are changed. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). shape: Shape name, or its 1-based index on the slide (required). bold, italic, underline: Font style toggles. font_name: e.g. "Calibri". font_size: Point size. font_color: Hex RGB, e.g. "FF0000" (with or without leading '#'). Returns: JSON confirmation. |
| format_shapeA | Format a shape's fill and outline. Only arguments that are explicitly set are changed. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). shape: Shape name, or its 1-based index on the slide (required). fill_color: Hex RGB fill color, e.g. "4472C4" (with or without '#'). line_color: Hex RGB outline color. line_weight: Outline weight in points. Returns: JSON confirmation. |
| get_speaker_notesA | Read the speaker notes for a slide. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). Returns: JSON with the notes text (empty string if there are none). |
| set_speaker_notesA | Set the speaker notes for a slide, replacing any existing notes. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). text: New notes text. Returns: JSON confirmation. |
| export_slide_to_imageA | Export a slide to an image file for visual verification. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). output_path: Destination file path (required). Extension selects the format: .png, .jpg, .bmp, or .gif. width, height: Output image dimensions in pixels. Returns: JSON with the exported file's absolute path. A vision-capable assistant can read the image back to check for overlapping shapes, text overflow, or layout regressions after an edit. |
| add_commentA | Add a comment to a slide (PowerPoint 2016+ modern comments). Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). text: Comment text (required). left, top: Position of the comment marker, in points. author: Comment author (default: MCP_AUTHOR env var, or "Author"). author_initials: Author initials (default: MCP_AUTHOR_INITIALS env var). Returns: JSON confirmation. |
| get_commentsA | List all comments on a slide. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). Returns: JSON with each comment's 1-based index, author, text, and position. |
| delete_commentA | Delete a comment from a slide. Args: presentation: Presentation name or path (None = active presentation). slide_index: 1-based slide index (required). index: 1-based comment index, from get_comments (required). Returns: JSON confirmation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Each tool targets a distinct resource-action combination: presentations, slides, shapes, text, notes, comments, and export. Even closely related tools like get_presentation_info vs list_slides are clearly differentiated—one provides overall slide metadata, the other a simple index/title list—while format_shape_text vs format_shape separate text styling from fill/outline.
All tool names follow a consistent snake_case verb_noun pattern: list_*, get_*, save_*, add_*, delete_*, duplicate_*, move_*, activate_*, set_*, format_*, export_*. No mixed conventions or vague verbs like 'process' or 'execute'.
23 tools is slightly over the typical sweet spot of 3–15, but the count is justified by the comprehensive breadth of PowerPoint automation (presentations, slides, shapes, notes, comments, export). Each tool serves a distinct purpose with no redundant or filler tools, making the scope reasonable for a mature MCP server.
The tool surface covers the full lifecycle of working with presentations, slides, shapes, notes, and comments, including read, create, update, delete, and navigation operations. The main gap is the lack of open/close/presentation creation tools—it only operates on already-open presentations—but this is a design limitation rather than an oversight, and the existing coverage handles all in-session edits.