# Manual RAG — SIH/SUS Query System

> Use this tool when you need to query Brazilian healthcare manuals and ordinances using natural language, and require advanced semantic search and regulatory critique analysis capabilities. It solves problems related to retrieving specific data from healthcare manuals and ordinances, and provides outputs such as relevant search results and data from SIGTAP and CNES. It is ideal for use cases involving complex healthcare information retrieval and analysis, accepting natural language inputs and providing relevant data as output.

Canonical page: https://skillsregistry.net/skills/leonardo-amaral-3-mcp-datasus  
JSON: https://api.skillsregistry.net/v1/skills/leonardo-amaral-3-mcp-datasus

## Description

A RAG-based MCP server for natural language querying of Brazilian healthcare manuals (SIH/SUS, SIA/SUS) and official ordinances. It provides 16 tools for semantic search, regulatory critique analysis, and retrieving data from SIGTAP and CNES.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/sl09mi4j5o)
- **Repository:** <https://github.com/leonardo-amaral-3/mcp-datasus>

## 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": "leonardo-amaral-3-mcp-datasus"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/leonardo-amaral-3-mcp-datasus` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/leonardo-amaral-3-mcp-datasus/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