medical-codes-mcp-server
Decodes, searches, validates, and crosswalks US medical codes (ICD-10-CM, ICD-10-PCS, HCPCS Level II) using an offline bundled index via MCP.
README
<div align="center"> <h1>medical-codes-mcp-server</h1> <p><b>Decode, search, validate, and crosswalk US medical codes — ICD-10-CM, ICD-10-PCS, HCPCS Level II — over a bundled offline index via MCP. STDIO or Streamable HTTP.</b> <div>6 Tools</div> </p> </div>
<div align="center">
</div>
<div align="center">
</div>
<div align="center">
</div>
[!NOTE] Informational, not clinical or coding advice. This server returns official code descriptions and billable/validity flags from public-domain federal releases to help you decode and look up codes. It is not medical advice, and a
valid_billableresult is not a coding or reimbursement decision. Always verify codes against the official source releases (CMS, CDC/NCHS, NLM) and your payer's rules before submitting a claim. The bundled data is only as current as the release baked into the build — callmedcode_list_systemsto see exactly which releases are active.
How it works
The code data is bundled inside the package — a single SQLite + FTS5 database (data/medical-codes.db) built at package-build time from the canonical federal source files and shipped in the npm tarball and Docker image. The server opens it read-only at startup and answers every tool call from disk.
That means the server is offline, keyless, and deterministic: no runtime network calls, no API key, no rate limit, single-tenant. The same inputs against the same bundled build always return the same output.
Bundled code systems
Only freely-redistributable, public-domain US federal code sets are bundled:
| System | Source | Covers |
|---|---|---|
| ICD-10-CM | CDC/NCHS — US federal, public domain | Diagnoses (billable leaf codes + non-billable category headers) |
| ICD-10-PCS | CMS — US federal, public domain | Inpatient procedures (axis-based 7-character codes) |
| HCPCS Level II | CMS — US federal, public domain | Supplies, drugs, and non-physician services |
RxNorm (NLM, public domain) — the drug-crosswalk layer (drug name ↔ RXCUI ↔ NDC, ingredients, brands) — is not bundled yet; it lands in a later release. Until then, medcode_map_codes' drug directions return a direction_unavailable error, and the hierarchy directions (parents/children) work today.
CPT (AMA copyright) and SNOMED CT / LOINC (UMLS-license-gated) are intentionally absent — they are not freely redistributable, so they cannot ship in an offline package.
US scope. ICD-10-CM and ICD-10-PCS are the US clinical modifications, not the WHO ICD-10/ICD-11 base or another country's national modification.
Tools
Six tools organized goal-first — one per user action, with a system discriminator instead of a per-system tool for each of the bundled code sets. All are read-only.
| Tool | Description |
|---|---|
medcode_get_code |
Decode 1–50 codes to their official descriptions. Auto-detects the system per code; partial-success found / notFound. |
medcode_search_codes |
Full-text search over official descriptions — go from a clinical description to the code. |
medcode_check_code |
Validate a code's existence, currency, and billability, with a whyNot for non-billable/terminated cases. |
medcode_map_codes |
Crosswalk a code within its hierarchy (parents/children); RxNorm drug directions land in a later release. |
medcode_browse_hierarchy |
Walk a system's hierarchy for discovery without a search term. |
medcode_list_systems |
List bundled systems with release identifiers, effective dates, and code counts (provenance). |
medcode_get_code
Decode one or more codes seen in a claim, EHR field, or another health server's output. The 80% entry point.
- Accepts 1–50 codes; mixed systems are fine — each code's system is detected independently from its shape
- Partial success: resolved codes in
found, unresolved innotFoundwith a per-code reason, so one bad code never fails the batch - An explicit
systemoverrides auto-detection when a value is genuinely ambiguous (an ambiguous code lists itscandidateSystems) includeHierarchyattaches each code's parent and immediate children- The resolved
systemis echoed on every result for chaining intomedcode_map_codesor a billability check
medcode_search_codes
Find codes whose official descriptions match a described concept — the reverse of medcode_get_code.
- Every search term must appear (prefix-matched), so
"diabetic neuropathy"returns codes mentioning both - Filter by
system,billableOnly(exclude headers/categories), andchapter - Ranked by full-text relevance; results echo the resolved system per row
- Discloses truncation when the result hits the cap, and returns an explicit notice (with the parsed query) when nothing matched
medcode_check_code
Validate whether a code is safe to submit, before a claim goes out.
- Discriminated status:
valid_billable,valid_not_billable,valid_header, orterminated - A
whyNotstring explains the non-billable and terminated cases (e.g. "valid ICD-10-CM category but not billable — submit a more specific child code") - Validity vs. existence is split: a non-billable or terminated code is a successful result with a
whyNot, not an error — only a code absent from every bundled system raisesunknown_code
medcode_map_codes
Crosswalk a code across systems and within a hierarchy.
- Hierarchy directions (available now):
parentsandchildrenwalk a code's prefix hierarchy (ICD-10-CM / HCPCS; ICD-10-PCS codes have no prefix parent) - Drug directions (
name_to_rxcui,ndc_to_rxcui,rxcui_to_ndc,rxcui_to_ingredients,rxcui_to_brands) are RxNorm-backed and returndirection_unavailableuntil RxNorm is bundled in a later release - Every result carries
sourceprovenance (which system or edge answered) so a chained call uses the right identifier
medcode_browse_hierarchy
Orient in an unfamiliar system or enumerate a category's specific codes, without a search term.
- With no
node: top-level entries (ICD-10-CM categories, HCPCS range buckets, or ICD-10-PCS first-axis values) - With a
node: its immediate children - ICD-10-CM and HCPCS use a prefix hierarchy (a shorter code is the parent of a longer one); ICD-10-PCS is axis-based — each of the 7 characters is an independent axis, so browsing returns valid next-position axis values, not prefix children
Features
Built on @cyanheads/mcp-ts-core:
- Declarative tool definitions — single file per tool, framework handles registration and validation
- Unified error handling — handlers throw, framework catches, classifies, and formats
- Typed per-tool error contracts — capable clients preview failure modes from
tools/list - Structured logging with optional OpenTelemetry tracing
- STDIO and Streamable HTTP transports
Domain-specific:
- Bundled SQLite + FTS5 index — offline, keyless, deterministic; no runtime network I/O, no rate limit
- Code-shape auto-detection routes a code to its system; an explicit
systemdisambiguates collisions - Real billable/validity signal from the source releases — the order-file billable flag drives
medcode_check_code, not a heuristic
Agent-friendly output:
- Provenance on every response — the resolved
systemis echoed for chaining, andmedcode_list_systemsreports exactly which release is baked into the running build - Graceful partial failure —
medcode_get_codereturns per-codefound/notFoundrows instead of failing the batch - Discriminated output contracts —
medcode_check_code's typed status andmedcode_map_codes'sourcelet callers branch on data, not string parsing
Getting started
This server ships with the code database bundled — there is no API key to obtain and nothing to download at runtime. Add the following to your MCP client configuration file.
{
"mcpServers": {
"medical-codes-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/medical-codes-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with npx (no Bun required):
{
"mcpServers": {
"medical-codes-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/medical-codes-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}
Or with Docker:
{
"mcpServers": {
"medical-codes-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "MCP_TRANSPORT_TYPE=stdio",
"ghcr.io/cyanheads/medical-codes-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
Refer to "your MCP client configuration file" generically — different clients use different config paths, and the server isn't client-specific.
Prerequisites
- Bun v1.3 or higher (or Node.js v24+ — the server falls back to the
better-sqlite3optional dependency when not run under Bun). - No API key, account, or network access required.
Installation
- Clone the repository:
git clone https://github.com/cyanheads/medical-codes-mcp-server.git
- Navigate into the directory:
cd medical-codes-mcp-server
- Install dependencies:
bun install
- Configure environment (optional):
cp .env.example .env
# all runtime vars are optional — the server runs as-is
Configuration
The server is offline and keyless — there are no required variables. Two server-specific knobs and the standard framework vars apply:
| Variable | Description | Default |
|---|---|---|
MEDCODE_DB_PATH |
Absolute path override for the bundled SQLite index. Set only to point at a custom-built or externally-mounted database. | packaged data/medical-codes.db |
MEDCODE_MAX_RESULTS |
Cap on rows returned by medcode_search_codes / medcode_browse_hierarchy. |
50 (ceiling 200) |
MCP_TRANSPORT_TYPE |
Transport: stdio or http. |
stdio |
MCP_HTTP_PORT |
Port for the HTTP server. | 3010 |
MCP_HTTP_ENDPOINT_PATH |
Endpoint path where the MCP server is mounted. | /mcp |
MCP_AUTH_MODE |
Auth mode: none, jwt, or oauth. |
none |
MCP_LOG_LEVEL |
Log level (RFC 5424). | info |
OTEL_ENABLED |
Enable OpenTelemetry instrumentation. | false |
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
Building the bundled index
The bundled data/medical-codes.db is committed and shipped — you only rebuild it when refreshing to a new federal release:
bun run scripts/build-index.ts
The script downloads the canonical .gov source files, parses them (ICD-10-CM/PCS order files, HCPCS ANWEB.txt), and emits the single .db file. It runs at build time only — the server never downloads anything.
Docker
docker build -t medical-codes-mcp-server .
docker run --rm -e MCP_TRANSPORT_TYPE=stdio medical-codes-mcp-server
The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/medical-codes-mcp-server. It copies the bundled data/medical-codes.db into the image so the server is fully self-contained. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.
Project structure
| Directory | Purpose |
|---|---|
src/index.ts |
createApp() entry point — registers the six tools and opens the bundled index in setup(). |
src/config |
Server-specific environment variable parsing and validation with Zod. |
src/mcp-server/tools |
Tool definitions (*.tool.ts). |
src/services/code-index |
The code-index service — read-only SQLite handle, code-shape detection, FTS5 query translation. |
scripts/build-index.ts |
Build-time ingest pipeline that bakes the federal source files into data/medical-codes.db. |
data/medical-codes.db |
The bundled SQLite + FTS5 code index, opened read-only at runtime. |
tests/ |
Unit and integration tests mirroring src/. |
Development guide
See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no
try/catchin tool logic - Use
ctx.logfor request-scoped logging; the code index is a read-only global, not tenant state - Register new tools via the
createApp()array insrc/index.ts - The bundled DB is the source of truth — surface real billable/validity flags from the source releases; never fabricate a code or a billability decision
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.