# depu-img-mcp

> depu-img-mcp — luyufan498-depu-image-understand-mcp. Use this tool when you need to enable text-only language models to understand images, or when you want to generate descriptive text from images. It solves problems such as image analysis and description by forwarding image and prompt requests to vision model backends, supporting multiple providers with task routing and safety checks. It takes image and prompt inputs and returns descriptive text outputs, ideal for use cases requiring image understanding and text generation.

Canonical page: https://skillsregistry.net/skills/luyufan498-depu-image-understand-mcp  
JSON: https://api.skillsregistry.net/v1/skills/luyufan498-depu-image-understand-mcp

## Description

Enables text-only language models to understand images by forwarding image and prompt requests to vision model backends via MCP, returning descriptive text. Supports multiple OpenAI-compatible providers with task routing and safety checks.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ktb9mdemnn)
- **Repository:** <https://github.com/luyufan498/depu-image-understand-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "luyufan498-depu-image-understand-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/luyufan498-depu-image-understand-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/luyufan498-depu-image-understand-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt