nih-umls-mcp: Instructions file for Claude Code

CLAUDE.md

nih-umls-mcp CLAUDE.md is an instructions file for Claude Code from feordin/nih-umls-mcp. It costs 629 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing a Python server that connects AI models to the NIH Unified Medical Language System and Value Set Authority Center APIs. It covers the project overview, installation commands, server startup, and tests.

In plain words
What is it for?
Use it when installing, running, testing, or extending the feordin/nih-umls-mcp project. The server provides access to medical terminology and healthcare value-set data through the Model Context Protocol.
Why use it?
It gives Claude Code repository-specific context and commands instead of making it infer how this medical terminology service is organised. It also explains that an UMLS API key is needed for live API calls.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is feordin/nih-umls-mcp's own configuration. It tells Claude Code how to work on nih-umls-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nih-umls-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to feordin/nih-umls-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/feordin/nih-umls-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/feordin/nih-umls-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nih-umls-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/feordin/nih-umls-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/feordin/nih-umls-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/feordin/nih-umls-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/feordin/nih-umls-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nih-umls-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/feordin/nih-umls-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/feordin/nih-umls-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 629 This file is loaded in full into every session.
When invoked 629 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00629 $0.00629
Opus 5 $0.00315 $0.00315
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 9d ago against content hash ec5e69e5310d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nih-umls-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP (Model Context Protocol) server that exposes NIH UMLS (Unified Medical Language System) REST API and NIH VSAC (Value Set Authority Center) FHIR API to AI models. Python package using mcp SDK and httpx for HTTP calls. Requires a UMLS API key via UMLS_API_KEY environment variable (same key works for both APIs).

Build & Development Commands

# Install in development mode
pip install -e .

# Install with dev dependencies (pytest)
pip install -e ".[dev]"

# Run the MCP server
python -m nih_umls_mcp.server

# Run tests
pytest

# Run the test server script (verifies tool registration, no API key needed)
python examples/test_server.py

# Run the client example (requires UMLS_API_KEY)
python examples/client_example.py

Architecture

Three-layer design:

  • src/nih_umls_mcp/umls_client.pyUMLSClient class: async HTTP client wrapping the UMLS REST API (https://uts-ws.nlm.nih.gov/rest). Handles auth via API key query parameter. Methods: search, get_cui, get_definitions, get_atoms, get_relations, get_source_concept, crosswalk.

  • src/nih_umls_mcp/vsac_client.pyVSACClient class: async HTTP client wrapping the VSAC FHIR API (https://cts.nlm.nih.gov/fhir). Handles auth via HTTP Basic Auth (username apikey, password is the UMLS key). Methods: search_value_sets, get_value_set, expand_value_set, validate_code, lookup_code, subsumes.

  • src/nih_umls_mcp/server.py — MCP server using mcp.server.Server. Defines 12 tools (6 UMLS + 6 VSAC) via @app.list_tools() and @app.call_tool() decorators. Uses lazily-initialized global UMLSClient and VSACClient instances. Runs over stdio transport.

The server tool names don't map 1:1 to client method names (e.g., get_concept tool calls client.get_cui(), crosswalk_codes tool calls client.crosswalk()).

Key Details

Read the full file on GitHub · 51 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 51 lines · 629 tokens per session scan A ec5e69e5310d

Subscribe to this mod's changes

nih-umls-mcp CLAUDE.md is an instructions file published in the GitHub repository feordin/nih-umls-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens