# Atlas MCP

> Use this tool when you need to efficiently search and converse over clinical documents in FHIR R4 format, leveraging AI-powered retrieval and ranking capabilities to solve complex healthcare data management problems. It accepts clinical document queries as input and outputs relevant search results, supporting multi-provider large language models and providing tools for agent queries, document retrieval, and session management. Ideal for use cases requiring secure and accurate clinical document analysis, such as medical research, patient data management, and healthcare analytics.

Canonical page: https://skillsregistry.net/skills/rsanandres-atlas-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rsanandres-atlas-mcp

## Description

AI-powered MCP server for searching and conversing over FHIR R4 clinical documents. Features hybrid retrieval (BM25 + pgvector), cross-encoder reranking, LangGraph multi-agent workflow, PII masking, and multi-provider LLM support (Ollama, OpenAI, Anthropic, Bedrock). 15+ tools for agent queries, document retrieval, session management, and embeddings ingestion.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/rsanandres/atlas_mcp)

## 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": "rsanandres-atlas-mcp"
    }
  }
}
```

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