# vision-mcp

> vision-mcp — yenns7-freeglm. Use this tool when you need to enhance text-only LLMs with visual capabilities, enabling them to analyze and understand images and videos through cloud vision models. It solves problems such as optical character recognition, visual grounding, and media information extraction, providing tools like vision chat and OCR. The vision-mcp tool accepts image and video inputs and returns relevant text-based outputs, making it ideal for applications requiring multimodal understanding.

Canonical page: https://skillsregistry.net/skills/yenns7-freeglm  
JSON: https://api.skillsregistry.net/v1/skills/yenns7-freeglm

## Description

Enables text-only LLMs to see images/videos via cloud vision models, offering vision chat, OCR, grounding, and media info tools with free GLM fallback.

## Trust

- **Trust score (0–1):** 0.65
- **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/d6zlypnvsm)
- **Repository:** <https://github.com/yenns7/freeglm>

## 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": "yenns7-freeglm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yenns7-freeglm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yenns7-freeglm/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