image-lab-mcp
# @0pvalencia/image-lab-mcp
MCP de imágenes: Openverse + Wikimedia Commons + atribución.
## Cursor / Claude / VS Code
### Local (recomendado si clonas el repo)
```json
{
"mcpServers": {
"image-lab": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/image-lab-mcp/dist/cli.js"]
}
}
}
```
Tras clonar: `npm install && npm run build`.
### npx (sin clonar)
```json
{
"mcpServers": {
"image-lab": {
"command": "npx",
"args": ["-y", "@0pvalencia/image-lab-mcp"]
}
}
}
```
> Si abres este repo en Cursor y usas `npx`, hace falta `npm install` en el proyecto para que el bin local exista. Sin eso, `npx` falla con `image-lab-mcp: not found` y el MCP se queda cargando.
## Install / run
```bash
npx -y @0pvalencia/image-lab-mcp
```
## Local
```bash
npm install
npm run build
npm start
```
## Tools
- `search_images` — query → `insertUrl` + `attribution`
- `format_attribution`
Usa `insertUrl` con `insert_image` de google-documents-mcp.
## License
MIT
TDQS
Scored across 2 tools
The two tools have completely separate functions: one searches for images, the other formats attribution text. There is no overlap or ambiguity between them.
Both tool names follow the same verb_noun pattern: 'search_images' and 'format_attribution'. The structure is consistent and intuitive.
With only 2 tools, the server feels minimal. While the tools cover a specific workflow (search and attribute), the count is at the low end, making it borderline but not unreasonable for a narrow purpose.
The pair of tools covers a search-and-attribution workflow, but the server name 'image-lab' suggests broader image capabilities that are missing. There are no tools for downloading, processing, or managing images, leaving notable gaps if the server intends to be a full image lab.