What is searchloinc CLAUDE.md?

Repository instructions for a small MCP server that lets language models search LOINC, the medical terminology system, through the same API used by the loinc.org search page. They describe its Python setup, credentials, endpoints, and development conventions.

Use them when developing, testing, or debugging the searchloinc server and its four search areas: terms, answer lists, parts, and groups.

They clarify the exact API contract and distinguish free-text LOINC search from the separate FHIR terminology service.

How jesse-smith/searchloinc configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jesse-smith/searchloinc. 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/jesse-smith/searchloinc/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jesse-smith/searchloinc

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jesse-smith/searchloinc/claude-md/github.svg)](https://agentmods.dev/instructions/jesse-smith/searchloinc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jesse-smith/searchloinc/claude-md"><img src="https://agentmods.dev/badge/instructions/jesse-smith/searchloinc/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jesse-smith/searchloinc/claude-md"><img src="https://agentmods.dev/badge/instructions/jesse-smith/searchloinc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,019 This file is loaded in full into every session.

When invoked 1,019 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.

Model	Per session	Once invoked
Fable 5.1	$0.01019	$0.01019
Opus 5.5	$0.00408	$0.00408
Sonnet 5.5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 2mo ago against content hash c8e21a64cb35, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

searchloinc 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 2mo 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 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.

What this is

A thin MCP server wrapping the LOINC Search API so LLMs can search LOINC the same way a human does via the loinc.org/search UI. Eventually intended to run as a Databricks app.

Stack: Python (FastMCP), managed with uv. Credentials via environment variables.

LOINC Search API contract

This wraps the documented Search API (https://loinc.regenstrief.org/searchapi/) — the same backend the loinc.org/search UI calls. Do not confuse it with the FHIR terminology service (fhir.loinc.org), which is a different, structured code-system API that does NOT reproduce the UI's free-text relevance ranking.

Docs: https://loinc.org/kb/api/search-api/ · auth: https://loinc.org/kb/api/auth/ · syntax: https://loinc.org/kb/search/basic and /kb/search/advanced-search-syntax
Four scoped GET endpoints — one MCP tool each is the intended design: /loincs (terms), /answerlists, /parts, /groups
Query params: query (required), rows, offset, sortorder (field asc|desc), language (int code from LinguisticVariants.csv), includefiltercounts (bool)
Auth: HTTP Basic with a LOINC username/password (register on loinc.org). Never hardcode — read LOINC_USERNAME / LOINC_PASSWORD from the environment.

Development

uv sync to install (--extra dev for ruff/pytest); uv run <cmd> to run inside the project venv (do not use system python3). toon-format is a prerelease pin (>=0.9.0b1).
Run the server: uv run python -m searchloinc (stdio transport). Or install it as a standalone command with uv tool install . and run searchloinc (same stdio server via the [project.scripts] entry point → searchloinc.__main__:main); pass creds through the MCP client's env block, since the installed command has no --env-file.
Test a live query end-to-end with the /loinc-search skill before trusting wrapper output.
Format/lint with ruff (via uv run ruff format / uv run ruff check). Note: a save hook runs ruff --fix, which strips not-yet-used imports — add an import in the same edit as its first use, or it vanishes before you reference it.

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 1,019 tokens per session scan A c8e21a64cb35

Subscribe to this mod's changes

searchloinc CLAUDE.md is an instructions file published in the GitHub repository jesse-smith/searchloinc (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,019 tokens to every session, about $0.0041 per session on Opus 5.5. 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.

searchloinc CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
searchloinc CLAUDE.mdjesse-smith/searchloinc	Instructions file	0	3mo ago	MIT	A	1,019	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

searchloinc: Instructions file for Claude Code