RDNLabs
🤖 AI-Powered Facility Management

MCP Server & AI Agent

Two AI integration layers: 515 tools (477 entity + 34 workflow + 4 utility) power the in-dashboard agent with constraint validation, facility snapshots, availability checks, schedule generation, time-off lifecycle, onboarding invites, booking invites, identity resolution, and specialty-aware demo seeding for infusion clinics, cancer centers, and medspas. A separate MCP server provides full API parity across 96 entity types for external AI clients like Claude Code and Cursor.

💬 Natural Language Administration

See how the FacLT Agent handles a multi-step scheduling request — from checking availability to confirming the booking in natural language.

FacLT Agent

Claude Sonnet 4 · 515 tools

Book Jane Smith for an IV Iron Infusion at the Downtown clinic tomorrow at 9am with Dr. Martinez in Bay 3
✓Facility Snapshot— Downtown Infusion Center — staff, stations, and services loaded
✓Availability Check— Dr. Martinez available tomorrow 9:00–12:00, Bay 3 open
✓Booking Validation— All constraints passed — staff, station, supply, hours, lead time
✓Booking Confirmed— Appointment created — estimated cost $485.00

Done! I've booked the appointment:

Patient: Jane Smith

Service: IV Iron Infusion (90 min)

Facility: Downtown Infusion Center

Station: Bay 3

Staff: Dr. Martinez

Time: Mar 13, 2026 at 9:00 AM

Status: Confirmed

⚙️ Architecture

The agent chat runs server-side through a Next.js API route. The user's auth token is forwarded to every MCP tool call, ensuring all actions respect permissions and tenant boundaries.

Admin UI

Chat Interface

API Layer

Streaming Proxy

AI Engine

Claude Models

Tool Layer

515 Tools

REST API

Business Logic

Database

Persistent Storage

Server-Side Execution

All tool calls execute on the server via the Next.js API route. No MCP credentials or API keys are exposed to the browser.

Authenticated Operations

Every tool call runs with the user’s identity, ensuring role-based access control and tenant scoping are enforced at every layer.

SSE Streaming

Responses stream via Server-Sent Events, delivering text token-by-token and tool call status updates in real time.

🛠️

MCP Tools Across 96 Entity Types

The MCP server exposes the full facility scheduling API surface as individually callable tools for external AI clients. Each tool includes parameter validation, safety guards, and detailed descriptions.

96
Entity Types
10
Domains
477
Operations
34
Workflow Tools
🏢
Organization
Multi-tenant organizations, system configuration, and administration
5 entities19 ops
🏥
Facilities
Facility configuration, stations, services, hours, and inventory
6 entities34 ops
🩺
People
Staff, clients, roles, employee types, emergency contacts, and reference data
10 entities59 ops
📅
Scheduling
Bookings, schedules, shifts, availability, time-off, booking invites, supplies, and audit logs
12 entities58 ops
📦
Services & Supply Chain
Service catalog, procedure code mappings, suppliers, inventory tracking, and procurement
7 entities39 ops
🛡️
Prior Authorization
PA lifecycle, requests, appeals, renewals, tasks, documents, transactions, subscriptions, payers, insurance, eligibility, clinical orders, and CMS code catalogs
34 entities167 ops
🔗
Messaging & Webhooks
Client and staff messaging, broadcasts, webhook subscriptions, onboarding invites, and event delivery
7 entities33 ops
🔔
Notifications
Multi-channel delivery, consent management, and device registration
7 entities25 ops
📇
Contact Info
Addresses, emails, phones, and type classifications
6 entities33 ops
🌎
Geography
Country and state reference data
2 entities10 ops
477 MCP Tools + 34 Workflow Tools + 4 Utility Tools

✨ Agent Features

Purpose-built chat interface with workflow-driven AI for facility scheduling administration.

Per-Conversation Model Selection

Choose the Claude model for each chat session — Haiku for quick queries, Sonnet or Opus for complex multi-step operations.

SSE Streaming

Real-time Server-Sent Events streaming delivers agent responses token-by-token as they are generated.

Tool Call Visualization

Every MCP tool call is displayed with expandable input/output, status indicators (running, success, error), and timing.

Persistent Chat History

Conversations are saved to localStorage so you can pick up where you left off across browser sessions.

Custom Markdown Rendering

Agent responses render rich markdown including tables, code blocks, lists, bold/italic, and inline code.

Destructive Action Safeguards

The MCP server includes safety guards that prevent deletion of system tenants, default roles, and reference data.

Auth Token Passthrough

The user's authentication token is forwarded to every MCP tool call, ensuring all actions respect RBAC and tenant scoping.

Mobile-Optimized Layout

Responsive chat interface adapts to any screen size with touch-friendly controls and compact tool call display.

🌱

Specialty-Aware Demo Seeding

Six workflow tools create realistic, fully-integrated demo environments tailored to three healthcare specialties. Each specialty brings its own service catalog, supply chain, staffing matrices, and facility configuration — seeded in dependency order so everything is cross-linked from day one.

Service Categories
BiologicIVIGIronNeurologySupportiveInjection
Sample Services
Remicade · Ocrevus · Gammagard · Tysabri · Venofer · Entyvio
Supplier Network
McKesson · Cardinal Health · Cencora
Dependency-Ordered Hydration
Seeding Pipeline
Entities are created in strict dependency order. Each phase completes before the next begins, ensuring every foreign key resolves and every record is cross-linked.
1
Service Catalog
Roles & Categories→
Services & Pricing→
Suppliers & Supplies
→
2
Facility Setup
Facilities & Stations→
Service Assignments→
Inventory Levels
→
3
Operations
Shifts & Schedules→
Staff & Availability→
Clients & Enrollment
3 entities
3 entities
3 entities
Full Hydration
Full Tenant Seeding
Creates a complete demo tenant with all data for the chosen specialty and size
Incremental Hydration
Seeds additional components into an existing tenant — full or partial
Incremental Generation
Staff Generation
Creates specialty-appropriate staff distributed across facilities
Client Generation
Creates clients with enrollment and cross-facility linking
Facility Generation
Creates facilities with configuration, contacts, stations, and inventory
Station Generation
Adds treatment stations with specialty-appropriate naming

Explore More

Dive into other areas of the platform.

Overview

Platform overview, tech stack, and project summary for the full FacLT scheduling system.

Features

Booking engine, schedule generation, patient self-scheduling, supply chain, dashboards, two-way SMS, and AI agent workflows.

Architecture

Eight-project architecture, 133 domain entities, CQRS layers, 95 API endpoint groups, 309 web components, and native mobile apps.

Mobile

Native Android apps for staff and patients built with Kotlin and Jetpack Compose, powered by the same REST API and MCP server.