mcp-server-cappt
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-capptgenerate an outline for a presentation about climate change"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-server-cappt: A MCP server for Cappt
Overview
A Model Context Protocol server for generating outline and presentation with cappt.cc.
Tools
generate_presentation
Generate a presentation from outline (generated by
generate_outline)Input:
outline(string): a standard outlineinclude_gallery(bool): whether to include gallery in resultinclude_preview(bool): whether to include preview in result
Returns:
record_id: the record ID of the generated presentationstatus: the status of the generation process'total_page: the total number of slides in the presentationeditor_url: the URL to edit the presentationtitle: the title of the presentationthumbanil: the thumbnail of the presentationgallery: the gallery of the presentationpreview: the preview of the presentation
Prompts
geenrate_outline
Generate a standard outline
Input:
input(string): user input, eg, title, article, etc.
Returns: A standard outline
Related MCP server: Marp MCP Server
Installation
cd path/to/repo
npm install
npm run buildConfiguration
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"sentry": {
"command": "node",
"args": [
"path/to/repo/dist/index.js"
],
"env": {
"CAPPT_TOKEN": "YOUR_CAPPT_TOKEN"
}
}
}
}Debugging
You can use the MCP inspector to debug the server. Please make sure you have installed this package with uv, then run:
npx @modelcontextprotocol/inspector node dist/index.tsLicense
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Available Tools
1 toolgenerate_presentationC
Generate presentation based on the outline generated by generate_outline
| Name | Required | Description | Default |
|---|---|---|---|
| outline | Yes | A standard outline generated by `generate_outline` | |
| include_gallery | No | Include gallery in the generation result | |
| include_preview | No | Include preview in the generation result |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states the basic action (generating a presentation). It does not mention side effects, authentication needs, output format, or any constraints. This is insufficient for understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise and front-loaded with the key purpose. It earns its place without extraneous information. However, it could be slightly more detailed without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has three parameters, no output schema, and no annotations, the description is incomplete. It does not explain what the tool returns, any side effects, or typical usage context. Agents would lack critical information to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all parameters with descriptions, achieving 100% coverage. The tool description adds no additional meaning beyond what the schema provides. Baseline score of 3 is appropriate; there is no added value but no deficiency.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a presentation based on an outline from `generate_outline`. It uses a specific verb and resource, and implies a pipeline dependency. While there are no sibling tools to differentiate from, the purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description only hints that the tool should be used after generating an outline. It provides no explicit guidance on when to use or avoid this tool, no prerequisites, and no alternatives. The lack of context for usage is a significant gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.5- First observed
generate_presentation
TDQS
Scored across 1 tool
Only one tool exists, so no ambiguity among tools. However, the tool description references a missing `generate_outline` tool, which could cause confusion about server capabilities.
Single tool, so no naming inconsistencies. The name `generate_presentation` follows a clear verb_noun pattern.
A single tool is insufficient for a presentation generation server, especially when it depends on a missing `generate_outline` tool.
The server lacks the required `generate_outline` tool that is referenced in the only tool's description, making the tool surface severely incomplete.
Maintenance
Related MCP Connectors
Generate, render, and host Slidev presentations from markdown
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
Generate polished PowerPoint presentations from text prompts, YouTube videos, or structured outlin…
Generate professional PowerPoint presentations from text, YouTube videos, or structured JSON data.…
Related MCP Servers
FlicenseAqualityDmaintenanceGenerate PowerPoint presentations using the Slidespeak API714-- AlicenseBqualityCmaintenanceEnables creation and management of Marp presentation projects with academic themes and structured slide layouts. Supports project initialization, slide generation with 6 layout templates, and integration with AI-powered editors like Claude Code and Cursor.377 npm11MIT
- AlicenseNot gradedqualityCmaintenanceEnables PowerPoint automation on Windows, including template-based creation, real-time editing, LaTeX equations, animations, and multimodal slide analysis, all via natural language.113MIT
- AlicenseAqualityDmaintenanceEnables AI-powered slide deck creation using natural language, allowing users to generate, edit, and manage presentations through MCP clients like Cursor and Claude Code.145 npmMIT