DentOps Copilot
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DentOps Copilot
An MCP-native agentic copilot for a dental practice. Given a dental X-ray + a patient record, a Claude agent orchestrates several MCP tools to detect findings, pull history, draft a patient-friendly summary and an insurance pre-authorisation narrative, and propose a recall — streaming every step live to a React dashboard over WebSocket. The MCP server (FastAPI + FastMCP) is callable by any MCP client, including Claude Desktop.
Portfolio prototype. Not a medical device. Every generated artifact is a draft for dentist review.

What I built vs. what's third-party
Mine: the FastMCP server (tools / resources / prompts over JSON-RPC), the Claude agent that orchestrates them through an MCP client, the grounded draft generation, the real-time WebSocket UI, and the deploy setup.
Third-party / mock: the imaging detector. It sits behind a
DetectorBackendinterface; the defaultMockDetectorreturns fixture findings. No model is trained here. Swap in an off-the-shelf detector via the interface.
Related MCP server: CornMCP
Quickstart
cp .env.example .env # add your ANTHROPIC_API_KEY
make install
make seed
make dev # API (uvicorn) + frontend (vite)
# open the printed localhost URL, click "Run demo · patient #1042"Architecture, tool contracts, and the event protocol are in SPEC.md. Build/finish notes for Claude Code are in CLAUDE.md. Deployment is in docs/DEPLOY.md.
Limitations & safety
Mock patient data and fixture detector output. No clinical validity; outputs are drafts only and route low-confidence findings to a dentist. Do not use with real patient data.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP-Native LLM Orchestration Agent
LLM Orchestration MCP Agent
LLM Orchestration Agent (Mcp)
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnd-to-end Prior Authorization decision-support system with a multi-agent AI pipeline, MCP Tool Registry, and PostgreSQL backend.1-
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to perform surgical code analysis, semantic memory, and quality enforcement via 18 specialized MCP tools, with a real-time analytics dashboard.67MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered dental X-ray analysis and treatment planning using YOLOv11 and clinical guideline RAG, integrated with MCP for use with Claude and other AI assistants.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables enterprise multi-agent decision workflows that expose 8+ MCP tools such as SQL query, web search, Python sandbox, RAG, file access, data cleaning, chart generation, and HTTP calls, orchestrated with LangGraph, streaming output, and human-in-the-loop approvals.MIT