# MCP-Grounded

> Use this tool when you need to classify medical images with a high degree of accuracy and safety, as it enables verification-aware abstention to skip uncertain cases. MCP-Grounded solves the problem of unreliable predictions in medical image classification by providing a pipeline for multi-agent verification. It takes medical images as input and outputs classified results with uncertainty awareness, ideal for use in high-stakes medical diagnosis applications.

Canonical page: https://skillsregistry.net/skills/silmun15-mcp-grounded  
JSON: https://api.skillsregistry.net/v1/skills/silmun15-mcp-grounded

## Description

Multi-agent pipeline for medical image classification with verification-aware abstention, enabling safer predictions by skipping uncertain cases.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zoytmmte4w)
- **Repository:** <https://github.com/silmun15/-mcp-grounded>

## 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": "silmun15-mcp-grounded"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/silmun15-mcp-grounded` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/silmun15-mcp-grounded/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