Compatible with every major AI agent and IDE
What is the CMS.gov Data MCP Server?
Connect to the Centers for Medicare & Medicaid Services (CMS) open data platform and query the US government's most comprehensive healthcare database.
What you can do
- Provider Search — Search 2.4 million+ Medicare-enrolled doctors and clinicians by name, specialty, or location, with NPI numbers and practice addresses
- Hospital Intelligence — Query hospital quality star ratings (1-5), types (Acute Care, Critical Access), and emergency services availability across all 50 states
- Nursing Home Lookup — Search skilled nursing facilities and long-term care homes with quality ratings and provider details
- Open Data Catalog — Browse and retrieve metadata from hundreds of CMS open datasets covering Medicare utilization, prescription drugs, and healthcare spending
How it works
- Subscribe to this server
- No API key required — CMS.gov is a public open data service
- Start querying healthcare data from Claude, Cursor, or any MCP-compatible client
Your AI agent gains direct access to the same data used by researchers, journalists, and policymakers to analyze the US healthcare system.
Who is this for?
- Healthcare Researchers — query provider enrollment data and hospital quality metrics without navigating government portals
- Journalists & Analysts — instantly retrieve Medicare provider statistics for data-driven reporting
- Patients & Caregivers — find doctors by specialty and location, compare hospital ratings
- Policy Professionals — access open datasets on healthcare spending, utilization, and outcomes
Built-in capabilities (8)
Returns the dataset title, full description, publication date, last modification date, and publisher information. Use the dataset ID obtained from list_datasets. Get detailed metadata for a specific CMS dataset
Returns the provider's full name, primary and secondary specialties, practice address, city, state, ZIP code, and Medicare enrollment status. NPI is a unique 10-digit number (e.g. "1234567890"). Get detailed provider information by NPI number
Filter by US state code (e.g. "CA", "NY", "TX") to see hospitals in that state. Returns overall ratings (1-5 stars), hospital type, and emergency services. Without a state filter, returns top-rated hospitals nationwide. Get hospital quality ratings, optionally by state
gov. Returns dataset identifiers, titles, descriptions, publication dates, and last-modified timestamps. The CMS data catalog includes datasets on Medicare utilization, hospital quality measures, provider enrollment, prescription drugs, and more. List available CMS open data datasets
Accepts names, specialties, cities, or states. Returns NPI numbers, full names, primary specialty, practice addresses, and Medicare enrollment IDs. The database covers 2.4 million+ active providers across the United States. Search for doctors and clinicians enrolled in Medicare
Accepts hospital names, cities, or states. Returns provider IDs, hospital names, types (Acute Care, Critical Access, etc.), overall quality ratings (1-5 stars), locations, and emergency services availability. Search for hospitals by name or location
Returns facility names, provider IDs, locations, and overall quality ratings. Useful for finding elder care facilities in a specific area. Search nursing homes and long-term care facilities
Examples: "Cardiology", "Internal Medicine", "Orthopedic Surgery", "Family Practice", "Dermatology", "Psychiatry". Returns matching providers with their NPI, name, practice location, and enrollment details. Search for healthcare providers by medical specialty
Why CrewAI?
When paired with CrewAI, CMS.gov Data becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call CMS.gov Data tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
CMS.gov Data in CrewAI
CMS.gov Data and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect CMS.gov Data to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for CMS.gov Data in CrewAI
The CMS.gov Data MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
CMS.gov Data for CrewAI
Every tool call from CrewAI to the CMS.gov Data MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Do I need an API key to use this server?
No. The CMS.gov Provider Data API is completely public and requires no authentication. Simply subscribe to this server to start querying Medicare provider data, hospital ratings, and open datasets immediately.
How current is the data?
CMS updates the Provider Data Catalog periodically, typically on a quarterly or monthly basis depending on the dataset. Hospital quality ratings are updated annually through the Hospital Compare program. All data is sourced directly from the official CMS.gov open data APIs.
What is an NPI number?
The National Provider Identifier (NPI) is a unique 10-digit identification number issued by CMS to every US healthcare provider. It's the universal standard for identifying doctors, hospitals, and healthcare organizations in Medicare and Medicaid transactions. You can search for any provider by their NPI using this server.
How does CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
Convertlab
8 toolsMarketing automation and customer data platform — manage customers, campaigns, and events via AI.

WooCommerce Alternative
10 toolsManage your WooCommerce store — audit products, orders, and reports via AI.

Clash Royale Tactical Intelligence
13 toolsThe definitive server for Clash Royale — track chest rotations, analyze battle decks, and monitor clan wars via AI.

Drupal
10 toolsManage headless content via Drupal — list nodes, handle taxonomy terms, manage files, and audit users directly from any AI agent.
