# deepsee

> deepsee — rikfish163-rgb-deepsee. Use this tool when you need to enhance text-only large language models (LLMs) with vision capabilities, enabling them to describe, recognize, and generate text from images. Deepsee achieves this by converting images to text via vision APIs, providing outputs such as image descriptions and OCR results. Ideal for use cases where LLMs require visual understanding, such as image-based question answering or text generation.

Canonical page: https://skillsregistry.net/skills/rikfish163-rgb-deepsee  
JSON: https://api.skillsregistry.net/v1/skills/rikfish163-rgb-deepsee

## Description

MCP server that gives text-only LLMs like DeepSeek vision capabilities by converting images to text via vision APIs, enabling image description, OCR, and generation in MCP clients.

## Trust

- **Trust score (0–1):** 0.42
- **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/b9jnciv3e8)
- **Repository:** <https://github.com/rikfish163-rgb/deepsee>

## 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": "rikfish163-rgb-deepsee"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rikfish163-rgb-deepsee` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rikfish163-rgb-deepsee/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