open-dental-mcp
Enables interaction with Open Dental practice management software, allowing reading of patients, appointments, providers, procedures, and recalls, as well as writing communications back to patient charts via MCP clients.
README
open-dental-mcp
Model Context Protocol (MCP) server for Open Dental — dental practice management software.
Talk to your Open Dental data from Claude, Cursor, or any MCP client. Read patients, appointments, providers, procedures, recalls. Write communications (phone calls, messages) back to patient charts.
Built against the Open Dental REST API. No existing MCP for Open Dental — this is the first.
What you can do with it
You: "Pull patient 4523 and show me their last 5 appointments + outstanding recalls."
Claude: *calls get_patient, then find_appointments, then find_recalls*
You: "Find every recall due this month and draft a friendly reminder for each."
Claude: *calls find_recalls with due_date window, drafts the messages*
You: "Just got off a call with the Smith family about rescheduling — log it."
Claude: *calls log_communication with the right comm_type + comm_mode*
You: "What providers are working at clinic 2 tomorrow?"
Claude: *calls list_providers + find_appointments, filters*
Install
pip install -e .
Configure
You need two API keys from Open Dental's Developer Portal:
- Developer API Key — applies to your integration (you register via
vendor.relations@opendental.com) - Customer API Key — generated per-customer in the Developer Portal
export OPENDENTAL_DEVELOPER_KEY="..."
export OPENDENTAL_CUSTOMER_KEY="..."
Who uses this server?
- Approved Open Dental API Partners building tools for dental practices. Your developer key + customer keys work directly.
- Dental practices / DSOs doing custom integration work. Email
vendor.relations@opendental.comto get set up.
Use with Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"open_dental_mcp": {
"command": "open_dental_mcp",
"env": {
"OPENDENTAL_DEVELOPER_KEY": "your-developer-key",
"OPENDENTAL_CUSTOMER_KEY": "your-customer-key"
}
}
}
}
Tools
| Tool | Type | What it does |
|---|---|---|
health_check |
Diagnostic | Verifies credentials |
get_patient |
Read | Fetch a patient by PatNum |
find_patients |
Read | Search by name / phone / email / DOB |
update_patient |
Write | Patch patient fields |
get_appointment |
Read | Fetch an appointment by AptNum |
find_appointments |
Read | List appointments (by date / patient / provider) |
create_appointment |
Write | Book a new appointment |
list_providers |
Read | All providers in the practice |
list_clinics |
Read | All clinics (offices) accessible |
list_operatories |
Read | Treatment rooms |
list_appointment_types |
Read | Cleaning / filling / exam definitions |
find_procedurelogs |
Read | Treatments performed |
log_communication |
Write | Log a phone call / email / message |
find_recalls |
Read | Hygiene follow-up reminders |
Common patterns
Pre-visit brief
User: I'm seeing patient 4523 at 2pm. Brief me.
Agent: get_patient(patnum=4523)
find_appointments(patnum=4523, limit=5)
find_procedurelogs(patnum=4523, limit=10)
find_recalls(patnum=4523)
→ Summary: patient info, last visits, what's been done, what's due
Recall campaign
User: Build this week's recall list and draft rebooking messages.
Agent: find_recalls(due_date_start="2026-06-26", due_date_end="2026-07-03")
→ for each: pull patient, draft a friendly message
Post-call documentation
User: Just took a call from the Smiths about rescheduling next week's cleaning.
Agent: find_patients(lname="Smith", fname="...", phone="...")
log_communication(
patnum=<found>,
comm_datetime="2026-06-26T15:30:00",
comm_type=1, # ApptRelated
comm_mode=2, # Phone
sent_or_received=1, # Received
note="Patient called to reschedule cleaning. Will call back with new date."
)
API coverage
| Open Dental endpoint | MCP tool |
|---|---|
GET /patients/{id} |
get_patient |
GET /patients |
find_patients |
PUT /patients/{id} |
update_patient |
GET /appointments/{id} |
get_appointment |
GET /appointments |
find_appointments |
POST /appointments |
create_appointment |
GET /providers |
list_providers |
GET /clinics |
list_clinics |
GET /operatories |
list_operatories |
GET /appointmenttypes |
list_appointment_types |
GET /procedurelogs |
find_procedurelogs |
POST /commlogs |
log_communication |
GET /recalls |
find_recalls |
Full Open Dental API: https://www.opendental.com/site/apispecification.html
Development
pip install -e ".[dev]"
pytest
open_dental_mcp
Need a custom MCP for your SaaS?
I build production-grade MCP servers for vertical SaaS — insurance, dental, veterinary, legal, property mgmt, home services. Typical engagement: 2-4 weeks, $25K-$120K. Source-owned, MIT-licensed, no vendor lock-in.
See sanjibani/mcp-services or email sanjibani@users.noreply.github.com.
Ships in the sanjibani vertical-MCP portfolio — see also hawksoft-mcp, open-dental-mcp, ezyvet-mcp, jobber-mcp, paid-skills, mcp-vertical-template.
MIT — see LICENSE.
Acknowledgements
- Open Dental for the public REST API
- Built using mcp-vertical-template
- Inspired by sanjibani/hawksoft-mcp (insurance vertical, same pattern)
See also
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.