MCP.Market

IntakeQ MCP server

by oktopeak·io.github.oktopeak/intakeq-mcp·v1.0.1
No reviews yet

IntakeQ/PracticeQ MCP connector with HIPAA §164.312(b) audit logging on every PHI read/write

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed IntakeQ MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

IntakeQ MCP tools (22, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit_export

    Export the local HIPAA §164.312(b) audit log. Every read and write of PHI is recorded here. Use date_from/date_to to filter by date range, client_id to filter by patient. Supports pagination via limit/offset.

  • auth_status

    Check whether the connector is authenticated with IntakeQ

  • clear_api_key

    Clear the stored IntakeQ API key

  • create_appointmentwrite action

    Create a new appointment in IntakeQ. All fields are required.

  • get_appointment

    Get a single appointment by ID

  • get_client

    Get a single client by ID (includes full profile). Response field reference: BillingType: 0=Unknown, 1=SelfPay, 2=Insurance LinkedClientRelationshipType: 0=None, 1=Parent, 2=Child, 3=Spouse, 4=Sibling, 5=Other, 6=Partner

  • get_form

    Get a single intake form submission by ID. PHI — every call is audit-logged.

  • get_invoice

    Get a single invoice by ID

  • get_note

    Get a single clinical note by ID. PHI — every call is audit-logged.

  • list_appointments

    List appointments. At least one of clientId, startDate, or endDate must be provided.

  • list_clients

    Search/list clients in the connected IntakeQ account. Returns up to 100 results per page. Response field reference: BillingType: 0=Unknown, 1=SelfPay, 2=Insurance LinkedClientRelationshipType: 0=None, 1=Parent, 2=Child, 3=Spouse, 4=Sibling, 5=Other, 6=Partner

  • list_files

    List file metadata for a client. Returns references only (Id, FileName, DateCreated, Size, ContentType, FolderId).

  • list_intake_forms

    List intake form submissions. PHI — every call is audit-logged.

  • list_invoices

    List invoices from the connected IntakeQ account

  • list_locations

    List locations configured in the IntakeQ account. Call this before create_appointment to find a valid LocationId.

  • list_notes

    List clinical notes. PHI — every call is audit-logged. Notes are read-only in IntakeQ.

  • list_practitioners

    List all practitioners in the IntakeQ account. Call this before create_appointment to find a valid PractitionerId.

  • list_questionnaire_templates

    List all questionnaire templates available in the IntakeQ account

  • list_services

    List services configured in the IntakeQ account. Call this before create_appointment to find a valid ServiceId.

  • send_intake_formwrite action

    Send an intake form to a client. Provide QuestionnaireId plus either ClientId or (ClientName and ClientEmail).

  • set_api_key

    Store your IntakeQ API key and verify connectivity

  • update_appointmentwrite action

    Update an existing appointment via PUT. Id and UtcDateTime are required. Cannot change client or practitioner.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan35 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 50 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How IntakeQ MCP compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,243 servers
Tools
22
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 18 read · 1 create · 2 change · 1 send or post

Install IntakeQ MCP in Claude Code, Cursor or VS Code

Runs npx -y @oktopeak/intakeq-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add intakeq-mcp -- npx -y @oktopeak/intakeq-mcp
Add to Cursor

What the publisher says

From the IntakeQ MCP repository's README, as published. We do not edit it. Read it on GitHub

@oktopeak/intakeq-mcp

### Built by Oktopeak — AI transformation & automation for healthcare practices

Digital transformation for healthcare and legal businesses. We build AI integrations, workflow automation, and custom software your practice owns outright — including this connector. → Book a 30-min call

IntakeQ/PracticeQ MCP connector for Claude. Gives Claude access to your IntakeQ scheduling, intake forms, treatment notes, invoices, and client records through the Model Context Protocol.

Every PHI read and write is logged locally in compliance with HIPAA §164.312(b).

⚠️ Before you connect this to real patient data

Two things must be in place before PHI flows through this connector:

Sign it in your IntakeQ account (Settings → HIPAA) before going live. This is one of IntakeQ's strengths: the BAA is self-serve and included in all plans.

  1. IntakeQ BAA — IntakeQ/PracticeQ includes a Business Associate Agreement.

Anthropic for inference. The defensible claim is training-disabled + Zero Data Retention under enterprise + BAA — not data locality. "Access" (the model processed it) is the exposure, not just retention. Sign up for Anthropic enterprise and request a BAA before using this with real patients.

  1. Anthropic enterprise tier with ZDR — With hosted Claude + MCP, PHI goes to

What this connector does:

  • Brokers authenticated calls to the IntakeQ REST API
  • Logs every PHI read and write to ~/.intakeq-mcp/audit.log (HIPAA §164.312(b))
  • Stores your API key encrypted (AES-256-GCM) locally — no PHI content stored (audit entries contain only access-trail identifiers)

Installation

npm install -g @oktopeak/intakeq-mcp

Claude Desktop configuration

{
  "mcpServers": {
    "intakeq": {
      "command": "intakeq-mcp"
    }
  }
}

Authentication

Generate your API key in IntakeQ: Settings → Integrations → Developer API

Then tell Claude:

"Set my IntakeQ API key to [your-key]"

Or use the MCP tool directly: setapikey

Tools

Tip: call listpractitioners, listservices, and listlocations before createappointment to obtain valid IDs required by that tool.

MCP Resources

HIPAA Audit Log

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

IntakeQ MCP: common questions

Is IntakeQ MCP server safe?
Mostly: it is graded B (80/100). Read the IntakeQ MCP safety report
How do I install IntakeQ MCP?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does IntakeQ MCP need an API key?
Yes. The registry entry asks for INTAKEQ_API_KEY, MCP_API_KEY.
Is IntakeQ MCP maintained?
The last commit was 90 days ago (2026-08-07). The latest release is v1.0.1.
How does IntakeQ MCP compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,243 servers); tools 22 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from oktopeak →