# ViperMCP

> Use this tool when you need to answer complex visual questions or ground objects in images, as it enables compositional and external knowledge-dependent image question answering through code generation and execution. ViperMCP takes in images and natural language questions as input and outputs accurate answers, leveraging multiple computer vision models. It is ideal for applications requiring visual understanding and reasoning, such as image analysis and visual question answering tasks.

Canonical page: https://skillsregistry.net/skills/ryansherby-vipermcp  
JSON: https://api.skillsregistry.net/v1/skills/ryansherby-vipermcp

## Description

A mixture-of-experts visual question-answering server that enables visual grounding, compositional image question answering, and external knowledge-dependent image question answering through code generation and execution. Built on the ViperGPT framework with support for multiple computer vision models including Grounding DINO, SegmentAnything, and GPT-4o.

## Trust

- **Trust score (0–1):** 0.31
- **Verification tier:** scanned
- **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:** [Glama](https://glama.ai/mcp/servers/stac8rl025)
- **Repository:** <https://github.com/ryansherby/ViperMCP>

## 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": "ryansherby-vipermcp"
    }
  }
}
```

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