MCP server: convert diagram images (screenshots, whiteboard photos, PDFs) into fully editable Visio/PPTX/draw.io/SVG files via LayerBack
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
git clone https://github.com/TopLocalAI/layerback-mcp{
"mcpServers": {
"layerback-mcp": {
"command": "node",
"args": ["/path/to/layerback-mcp/dist/index.js"]
}
}
}Resumen de MCP Servers
# LayerBack MCP Server
Give your AI agent the one diagram skill it's missing: turning **pictures of
diagrams into fully editable files**.
Agents can write Mermaid — but when the input is a screenshot, a whiteboard
photo, or a diagram trapped in a PDF page, they're stuck. This MCP server
connects any MCP-compatible agent (Claude Desktop, Claude Code, Cursor, …) to
[LayerBack](https://layerback.com), which rebuilds every shape, connector, and
label as a native object and returns **Visio (VSDX), PowerPoint (PPTX),
draw.io, and SVG** — all editable, from one conversion.
## Tools
| Tool | What it does |
|---|---|
| `convert_diagram_image` | Convert a local image file (PNG/JPG/WebP); waits for the result by default (~30–60 s) |
| `get_conversion_status` | Poll a running job |
| `download_converted_diagram` | Save any output format to a local path |
## Setup
1. Create an API key at <https://layerback.com/settings/apikeys>
(new accounts include free credits — one conversion costs 10 and includes
every output format).
2. Add the server to your MCP client config:
```json
{
"mcpServers": {
"layerback": {
"command": "npx",
"args": ["-y", "layerback-mcp"],
"env": { "LAYERBACK_API_KEY": "your-key-here" }
}
}
}
```
## Example prompts
- "Convert ~/Desktop/whiteboard.jpg into a Visio file and save it to my
Downloads folder."
- "Here's a screenshot of our architecture diagram — rebuild it as an
editable draw.io file."
- "Batch-convert every PNG in ./legacy-diagrams to VSDX."
## Notes
- Requires Node 18+.
- REST API docs: <https://layerback.com/docs/api> ·
OpenAPI: <https://layerback.com/openapi.yaml>
- Files upload to LayerBack for conversion and are deleted within 72 hours.
MIT © LayerBack
Lo que la gente pregunta sobre layerback-mcp
¿Qué es TopLocalAI/layerback-mcp?
+
TopLocalAI/layerback-mcp es mcp servers para el ecosistema de Claude AI. MCP server: convert diagram images (screenshots, whiteboard photos, PDFs) into fully editable Visio/PPTX/draw.io/SVG files via LayerBack Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-08-05.
¿Cómo se instala layerback-mcp?
+
Puedes instalar layerback-mcp clonando el repositorio (https://github.com/TopLocalAI/layerback-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar TopLocalAI/layerback-mcp?
+
Nuestro agente de seguridad ha analizado TopLocalAI/layerback-mcp y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene TopLocalAI/layerback-mcp?
+
TopLocalAI/layerback-mcp es mantenido por TopLocalAI. La última actividad registrada en GitHub es del 2026-08-05, con 0 issues abiertos.
¿Hay alternativas a layerback-mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega layerback-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/toplocalai-layerback-mcp)<a href="https://claudewave.com/repo/toplocalai-layerback-mcp"><img src="https://claudewave.com/api/badge/toplocalai-layerback-mcp" alt="Featured on ClaudeWave: TopLocalAI/layerback-mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!