npi-providers-mcp-server

Tools

Three tools covering the provider directory — search the registry, decode an NPI to its full record, and resolve plain-language specialties through the bundled taxonomy:

npi_search_providers

Search the registry for individual practitioners and organizations, with specialty resolution and honest pagination disclosure.

• Search by name_search shortcut, explicit first_name / last_name, organization_name, city / state / postal_code, and provider_type (individual / organization)

• Plain-language specialty (e.g. "cardiologist") resolves through the bundled NUCC taxonomy to the registry's exact descriptions before searching; the resolved taxonomy is echoed back so you can see what was actually searched

• taxonomy_description escape hatch for callers who already hold an exact NUCC description (mutually exclusive with specialty)

• Trailing-wildcard (*) name matching, with the registry's ≥2-leading-character rule documented inline

• Discloses that the returned count is the page size — never a grand total — and that only the first 1200 matches are reachable, steering broad queries toward narrower filters

npi_get_provider

Decode one or more NPIs into fully populated provider profiles — the tool to turn an NPI from a claim, prescription, or another health data source into a known provider.

• Batch fetch up to 10 NPIs per call; the 10-digit format is validated before any API call

• Returns every taxonomy (with its primary flag, license number and state), all practice and mailing addresses, credential, sex, sole-proprietor flag, enumeration and last-updated dates, secondary identifiers (Medicaid, etc.), and FHIR/Direct endpoints

• Partial-success reporting — well-formed NPIs with no registry record (deactivated or never enumerated) land in notFound rather than failing the whole call

npi_lookup_taxonomy

Resolve and browse the NUCC Healthcare Provider Taxonomy — the specialty code set NPPES uses — fully offline from the bundled code set.

• resolve — turn a plain-language specialty into matching taxonomy codes and canonical descriptions (the value the search tools filter on)

• get — return the full entry for an exact taxonomy code

• browse — walk the hierarchy (grouping → classification → specialization), filterable by grouping and by NPI section (Individual/NPI-1 vs Non-Individual/NPI-2)

Related MCP server: NPI MCP Server

Resources and prompts

All resource data is also reachable via tools. The resources are convenience twins for resource-capable clients; tool-only clients lose nothing.

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool and resource definitions — single file per primitive, framework handles registration and validation

• Unified error handling — handlers throw, framework catches, classifies, and formats

• Pluggable auth: none, jwt, oauth

• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1

• Structured logging with optional OpenTelemetry tracing

• STDIO and Streamable HTTP transports

NPI/NPPES-specific:

• Keyless — runs against the public CMS NPPES NPI Registry API (v2.1) with no API key or account

• Bundled NUCC taxonomy — the 879-code Healthcare Provider Taxonomy (v25.0) ships in the image and loads into an in-memory index at startup, so specialty resolution and code lookups work fully offline with no second upstream

• Specialty resolution turns a vague term ("heart doctor") into the precise taxonomy description the registry filters on, and echoes the match back for the agent to verify

• Detects the registry's quirk of returning HTTP 200 with an Errors[] body on validation failure and maps it to typed, recoverable error reasons

Agent-friendly output:

• Provenance on search — the resolved taxonomy and the exact taxonomy_description sent to the registry are echoed back, so agents can see what was actually searched and re-run with a different code

• Honest pagination — the returned count is disclosed as the page size, never a fabricated grand total, with the 1200-match reachable ceiling surfaced when a broad query is capped

• Graceful partial failure — npi_get_provider returns per-NPI found / notFound rows instead of failing the whole batch when some NPIs are deactivated or never enumerated

Getting started

Add the following to your MCP client configuration file. No API key is required — the upstream NPPES registry is keyless.

{
  "mcpServers": {
    "npi-providers-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/npi-providers-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "npi-providers-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/npi-providers-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "npi-providers-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/npi-providers-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.2 or higher (or Node.js v24+).

• No API key — the NPPES NPI Registry API is public and keyless. The NUCC taxonomy is bundled, so there is no second data source to provision.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/npi-providers-mcp-server.git

2. Navigate into the directory:

cd npi-providers-mcp-server

3. Install dependencies:

bun install

4. Configure environment (optional):

cp .env.example .env
# edit .env only if you need to override the NPPES base URL or timeout

Configuration

No required variables — the server runs out of the box against the keyless NPPES registry. All variables below are optional overrides.

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker build -t npi-providers-mcp-server .
docker run --rm -e MCP_TRANSPORT_TYPE=http -p 3010:3010 npi-providers-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/npi-providers-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

• Register new tools and resources in the createApp() arrays

• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Provider data from the CMS NPPES NPI Registry (public domain). Specialty codes from the NUCC Health Care Provider Taxonomy (NUCC, bundled).