Healthcare Analytics

Quick setup of an MCP for common healthcare data pulls

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "dslans-mcp_healthcare_data": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--pull=always",
        "-v",
        "/path/to/your/service-account.json:/app/credentials.json:ro",
        "-e",
        "GOOGLE_APPLICATION_CREDENTIALS=/app/credentials.json",
        "-e",
        "GCP_PROJECT_ID=your-gcp-project-id",
        "-e",
        "BIGQUERY_DATASET_PREFIX=your-dataset-prefix",
        "ghcr.io/dslans/mcp_healthcare_data:latest"
      ],
      "env": {
        "GCP_PROJECT_ID": "your-gcp-project-id",
        "BIGQUERY_DATASET_PREFIX": "your-dataset-prefix",
        "GOOGLE_APPLICATION_CREDENTIALS": "/app/credentials.json"
      }
    }
  }
}

You have a healthcare analytics MCP Server that provides ready-to-use analytics tools for value-based care, quality measures, utilization, and financial metrics. It’s designed to answer common data questions with repeatable queries, so analysts can focus on deeper analyses while teams get fast, reliable insights from unified data.

How to use

You interact with the MCP server through your MCP client (for example, Claude Desktop or Warp). The server exposes a suite of healthcare analytics tools that return structured data you can use in reports and dashboards. Common use patterns include building population health dashboards, tracking PMPM and cost trends, measuring quality performance, identifying high-cost patients for care management, and monitoring readmission patterns. You can combine multiple tools in a workflow to generate a comprehensive view of population health, cost drivers, utilization, and care gaps.

Practical usage tips:

Start with demographic and utilization summaries to understand the population baseline.
Then run PMPM analyses to see financial trends across service categories.
Add quality measures to evaluate performance and identify improvement areas.
Identify high-cost patients and readmission patterns for targeted care management.
Use HCC risk scores to prioritize risk adjustment and stratification efforts.

Available tools

get_patient_demographics

Returns demographic breakdown including age groups, gender distribution, and total patient counts for a specified date range.

get_utilization_summary

Provides utilization metrics such as claims counts, costs, and service category breakdowns within a date range.

get_pmpm_analysis

Calculates Per Member Per Month costs across service categories with optional payer filters and trend outputs.

get_quality_measures_summary

Returns quality measure performance rates and compliance flags for HEDIS and clinical measures for a given year.

get_chronic_conditions_prevalence

Analyzes prevalence of chronic conditions across the population for a given year.

get_high_cost_patients

Identifies patients exceeding a specified cost threshold to prioritize case management.

get_readmissions_analysis

Calculates 30-day readmission rates and patterns, with optional condition filters.

get_hcc_risk_scores

Provides HCC risk score distribution and population risk stratification for a given year.

Built by

VeilStrat

AI signals for GTM teams