# OpenRouter Vision

> Use this tool when you need to analyze images using AI-powered vision models, solving problems such as image classification, object detection, and content understanding. It accepts image inputs via file paths, URLs, or base64-encoded data and provides configurable analysis capabilities through a single interface. Ideal for developers integrating vision analysis into their applications, it supports multiple models and handles various input formats with robust error handling.

Canonical page: https://skillsregistry.net/skills/openvision  
JSON: https://api.skillsregistry.net/v1/skills/openvision

## Description

MCP OpenVision provides image analysis capabilities through OpenRouter's vision models, enabling AI assistants to analyze images via file paths, URLs, or base64-encoded data. Built with Python using the FastMCP framework, it offers a single configurable tool that accepts contextual queries and system prompts to guide analysis, supporting multiple OpenRouter vision models including Claude, GPT-4o, and Qwen variants. The implementation handles various image input formats, includes proper error handling for API failures, and is designed for developers who need reliable vision analysis integration in their MCP-compatible applications without managing direct API connections or image encoding complexities.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/openvision)
- **Repository:** <https://github.com/mikeysrecipes/mcp-openvision>

## 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": "openvision"
    }
  }
}
```

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