Healthcare Provider MCP (NPI)

An MCP server that lets AI agents (Claude, ChatGPT, Cursor, and any MCP client) search and look up US healthcare providers from the official public NPI Registry — doctors, nurses, pharmacies, clinics, hospitals.

Built on the same precision-first engine as the NPI Registry scraper: every search result is verified to actually match your query (the NPI API silently returns noise for broad common names; this server filters it out).

Two ways to use it

1. As an MCP server (for AI agents)

When run in Standby mode, the Actor exposes an MCP endpoint at /mcp (Streamable HTTP, JSON-RPC 2.0). Point any MCP client at the Actor's Standby URL + /mcp, or call it through Apify's MCP integration using actorName:toolName.

Tools:

Tool	Arguments	Returns
search_providers	lastName, firstName, organizationName, taxonomy, city, state, providerType (any/individual/organization), limit (1–200)	Array of verified providers
get_provider	npi (10-digit)	A single provider record

Example tools/call:

{ "jsonrpc": "2.0", "id": 1, "method": "tools/call",
  "params": { "name": "search_providers",
    "arguments": { "taxonomy": "Cardiology", "city": "Austin", "state": "TX", "limit": 10 } } }

2. As a normal Actor (batch / testing)

Run it with input and it executes one tool, storing results in the dataset:

{ "tool": "search_providers", "lastName": "Smith", "state": "TX", "taxonomy": "Family Medicine", "limit": 20 }

{ "tool": "get_provider", "npi": "1760914097" }

Output fields

npi, enumerationType, providerName, credential, organizationName, primaryTaxonomy, primaryTaxonomyCode, addressLine1, city, state, postalCode, phone, npiUrl.

Pricing

Pay per event — priced per tool call (e.g. per search_providers / get_provider action). Per-action pricing is ideal for agent workloads.

Reliability

• Verified matches only (post-filtering defeats the NPI API's broad-query noise).
• Exponential backoff on rate limits / server errors.
• Stateless MCP server — no sessions to leak, no proxies, no credentials.

Data usage & compliance

All data comes from the public NPI Registry operated by CMS, published in the public domain. This server performs only lookups against the official public API. Use the data in accordance with applicable laws; do not use it for spam or harassment.

How to use Healthcare Provider MCP (NPI)

1. Open Healthcare Provider MCP (NPI) on Apify Store and click Try for free.
2. Fill in the input (the form is prefilled with a working example) and click Start.
3. Watch results appear in the Output tab, then download them as JSON, CSV, Excel or HTML, or read them through the API.
4. Optional: save the input as a task and add a schedule to run it automatically, or connect it to your tools with integrations and webhooks.

Input example

{
  "tool": "search_providers",
  "lastName": "Smith",
  "state": "CA",
  "limit": 5
}

All fields are described in the Input tab, and the same JSON works in the API and for AI agents.

Use Healthcare Provider MCP (NPI) with AI agents (MCP)

Give Claude, ChatGPT, Cursor, VS Code or any MCP client this Actor as a tool through the hosted Apify MCP server. The agent sees the input fields with descriptions and example values, runs the Actor, and reads the results.

MCP server URL (this Actor only):

https://mcp.apify.com/?tools=technicaldost/healthcare-provider-mcp

Claude Code:

$claude mcp add --transport http apify "https://mcp.apify.com/?tools=technicaldost/healthcare-provider-mcp" --header "Authorization: Bearer YOUR_APIFY_TOKEN"

Cursor, VS Code, Claude Desktop and other clients (mcp.json or the client's MCP settings):

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=technicaldost/healthcare-provider-mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

Clients that support sign-in (such as Claude.ai connectors) can use the URL without a token and log in to Apify instead. Get your token in Apify Console → Settings → API & Integrations, or generate a ready config for your client at mcp.apify.com. In the agent the tool is named technicaldost--healthcare-provider-mcp; ask it, for example, to "run Healthcare Provider MCP (NPI) with {"tool": "search_providers", "lastName": "Smith", "state": "CA", "limit": 5}".

AI agents without an Apify account can also run and pay for this Actor per request with x402 agentic payments.

Run Healthcare Provider MCP (NPI) via API

Run the Actor and get its results in one call (replace YOUR_APIFY_TOKEN):

curl -X POST "https://api.apify.com/v2/acts/technicaldost~healthcare-provider-mcp/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"tool": "search_providers", "lastName": "Smith", "state": "CA", "limit": 5}'

Python (pip install apify-client):

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("technicaldost/healthcare-provider-mcp").call(run_input={"tool": "search_providers", "lastName": "Smith", "state": "CA", "limit": 5})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

JavaScript / TypeScript (npm install apify-client):

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('technicaldost/healthcare-provider-mcp').call({"tool": "search_providers", "lastName": "Smith", "state": "CA", "limit": 5});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Long runs: start them with POST /v2/acts/technicaldost~healthcare-provider-mcp/runs and fetch the dataset when the run finishes, or receive a webhook.

Related Actors

• Healthcare Intelligence Scraper — Extract healthcare provider data from NPI registry, Healthgrades, Zocdoc directories

FAQ

Can I use Healthcare Provider MCP (NPI) with AI agents like Claude or ChatGPT?

Yes. Connect the Apify MCP server with ?tools=technicaldost/healthcare-provider-mcp (see above) and the agent can run the Actor and read its results on its own.

Can I call Healthcare Provider MCP (NPI) from my own code?

Yes. Use the REST API, or the official Python and JavaScript clients shown above. Results are available as JSON, CSV, Excel, XML or HTML.

How do I run it on a schedule?

Save your input as a task in Apify Console and add a schedule (for example, daily). Use webhooks or integrations to send each run's results onward.

Is it legal to use this Actor?

It works with publicly available data. Make sure your use complies with the source website's terms and with data protection laws such as GDPR, especially for personal data.

Something doesn't work or I need a feature. What should I do?

Open an issue in the Issues tab on this Actor's page with an example input, and we'll look into it.