violet-fhir
Exposes a FHIR endpoint as deterministic read-only tools, providing a context layer for retrieving clinical data from FHIR servers.
README
violet-fhir
Status: Pre-build — the MCP tool layer is in progress. Nothing here works yet.
1. What this is
A FHIR data substrate plus a guideline retrieval layer, connected by an agent loop.
Two halves:
- Context layer — an MCP server exposing a FHIR endpoint as deterministic tools. Read-only. This is the foundation everything else sits on.
- Guideline layer — retrieval with citations over public clinical practice guidelines. Never sees patient data.
The output is always a cited draft for a pharmacist, never an assertion and never an action.
2. Why it exists
- A portfolio artifact that demonstrates MCP, RAG, agent loops, and A2A in a clinical context.
- VA/DoD Clinical Practice Guidelines are authoritative, freely published documents — and they live as PDFs. A June 2026 VA OIG review of generative AI chat tools in clinical use found that VA does not curate the prompts staff use for clinical care and documentation, with sharing happening informally instead. The demand for AI assistance at the point of care is real and already being met without provenance. VA OIG 26-00182-140
3. What this is NOT
- Not clinical decision support. This is retrieval with provenance. The pharmacist remains the decision-maker; the system's job is to show its work.
- Not write-enabled. Read-only against FHIR. No order placement, no chart write-back, ever.
- Not PHI-touching in development. Synthetic data only (SMART sandbox, HAPI public server, Synthea).
- Not a product. Portfolio artifact and community contribution. If it becomes a product later, that's a separate decision made on purpose.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.