# deepseek-vision-mcp

> Use this tool when you need to recognize and identify objects within images using AI-powered vision capabilities. It solves problems such as image classification, object detection, and scene understanding, and accepts image files as input, returning recognition results as output. Ideal for use cases where automated image analysis is required, such as content moderation, product identification, or surveillance applications.

Canonical page: https://skillsregistry.net/skills/m77can-deepseek-vision-mcp  
JSON: https://api.skillsregistry.net/v1/skills/m77can-deepseek-vision-mcp

## Description

Provides a recognize_image tool that enables image recognition using DeepSeek's vision capabilities. Supports automatic login via browser or manual token configuration for server environments.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/m31m2jryxn)
- **Repository:** <https://github.com/m77can/deepseek-vision-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": "m77can-deepseek-vision-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/m77can-deepseek-vision-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/m77can-deepseek-vision-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