# M3

> Use this tool when you need to query large medical datasets using natural language, to solve problems such as retrieving specific patient information or analyzing medical trends. It takes in natural language queries as input and outputs relevant data from the MIMIC-IV dataset, supporting both local and cloud-based data storage. Ideal for healthcare professionals and researchers working with medical data, M3 provides a user-friendly interface to access and analyze complex medical information.

Canonical page: https://skillsregistry.net/skills/rafiattrach-m3  
JSON: https://api.skillsregistry.net/v1/skills/rafiattrach-m3

## Description

Enables querying MIMIC-IV medical data using natural language through MCP clients, with support for local DuckDB and cloud BigQuery backends.

## Trust

- **Trust score (0–1):** 0.52
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lmyby0vsrx)
- **Repository:** <https://github.com/rafiattrach/m3>

## 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": "rafiattrach-m3"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rafiattrach-m3` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rafiattrach-m3/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