
Dingdawg Healthcare Agent
io.github.dingdawgPublished by GitHub account dingdawgv2.0.7Updated Oct 27, 2026
HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.
Overview
Local MCP server for HIPAA-aware clinical workflows: patient intake, clinical summaries, compliance checks and appointment scheduling.
- What you can do
- Generate structured patient intake forms and AI-assisted intake
- Produce clinical summaries from notes, with ICD-10 and CPT code references on the paid tier
- Run HIPAA compliance checks with safeguard gap identification and scores
- Schedule appointments, with AI-optimized scheduling and conflict detection on the paid tier
- Return structured JSON with a governance receipt on every call for audit trails
- When to use it
- Useful for clinics, health-tech developers or compliance teams that want an assistant to draft intake forms, clinical documentation, HIPAA gap checks and scheduling steps in one chain. The free tier suits local, no-transmission experimentation; the paid tier is for LLM-powered clinical analysis.
- Requirements
- Runs locally via npx (Node.js). An API key in DINGDAWG_API_KEY is needed for paid-tier access; the free tier runs locally without one. Desktop MCP client only; no web execution.
Installation
In SourceWeft
- Open Dingdawg Healthcare Agent in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
dingdawg-healthcare-agent
Breakthrough clinical workflow bottlenecks. AI healthcare assistance that respects HIPAA from day one.
HIPAA-aware AI for patient intake, clinical summaries, compliance checking, and appointment scheduling. Free tier runs locally with zero data transmission. Paid tier provides LLM-powered clinical analysis via HIPAA-compliant API. Every action is governed and receipted.
For AI Assistants
This MCP server returns structured JSON for seamless integration:
- ICD-10 and CPT code references in clinical summaries
- HIPAA compliance scores with specific safeguard gap identification
- Governance receipt on every call (audit-ready)
- Chain-ready:
patient_intake->hipaa_checkto verify compliance ->clinical_summaryfor documentation ->appointment_schedulerfor follow-up
Composable with any MCP client: Claude Code, Cursor, VS Code, ChatGPT Desktop, Windsurf.
Install
Claude Code
Cursor
Add to .cursor/mcp.json:
Full Stack (all 13 agents)
Tools
Pricing
- Free: 10 intakes/day, local processing (no data leaves your machine)
- Pro: $49/mo, 100 calls/day, AI-powered clinical analysis
- Pay-as-you-go: $0.25/call, no commitment
Get API key: https://dingdawg.com/developers
Governed
Every call is receipted and auditable. HIPAA checks reference specific administrative, physical, and technical safeguards (45 CFR Part 164). Clinical summaries include disclaimer that content is for informational purposes and does not constitute medical advice. All PHI processing on paid tier uses HIPAA-compliant infrastructure.
Support
Source: README.md at commit 5e0ca4e
Tools
0Version history
1- v2.0.7LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.