What is tebra-mcp-server CLAUDE.md?

A set of instructions for developing a Tebra/Kareo MCP server. Tebra and Kareo are healthcare practice-management systems; the server connects to their SOAP and FHIR APIs, which are standards for exchanging structured service and clinical data.

Use it when building, testing, or changing the server’s healthcare API requests and MCP tools.

It documents the required environment settings, commands, project structure, and tests needed to develop and run the server safely.

How jamesrosing/tebra-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jamesrosing/tebra-mcp-server. 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/jamesrosing/tebra-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jamesrosing/tebra-mcp-server

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/jamesrosing/tebra-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/jamesrosing/tebra-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jamesrosing/tebra-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jamesrosing/tebra-mcp-server/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/jamesrosing/tebra-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jamesrosing/tebra-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,216 This file is loaded in full into every session.

When invoked 4,216 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	$0.04216	$0.04216
Opus 5.5	$0.01686	$0.01686
Sonnet 5.5	$0.00843	$0.00843
Haiku 4.5	$0.00422	$0.00422

Measured 2mo ago against content hash 46bf28415539, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tebra-mcp-server 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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

MCP server that wraps the Tebra/Kareo SOAP API v2.1 and FHIR R4 API, exposing practice management and clinical data operations as MCP tools over stdio transport. Published to npm as tebra-mcp-server.

Tool count: 34 SOAP tools + 13 FHIR tools = 47 total.

Commands

npm run build        # tsc — compiles to dist/
npm run dev          # tsx src/index.ts — runs directly without build
npm start            # node dist/index.js — runs compiled output
npm test             # node:test via tsx — src/__tests__/*.test.ts

Tests use node:test through tsx (no framework install). src/__tests__/request-shapes.test.ts pins the WSDL-derived request body for every builder — run it after touching ANY request XML; the live failure mode for a wrong body is a silent empty result, not an error. No linter is configured.

Required Environment Variables

SOAP (required): TEBRA_SOAP_USER, TEBRA_SOAP_PASSWORD, TEBRA_CUSTOMER_KEY — validated at startup by getConfig(). Optional: TEBRA_SOAP_ENDPOINT (defaults to Kareo production endpoint).

FHIR (optional): TEBRA_FHIR_CLIENT_ID plus EITHER TEBRA_FHIR_PRIVATE_KEY_PATH + TEBRA_FHIR_KID (SMART Backend Services private_key_jwt, RS384 client assertion — preferred, and the only auth a JWKS-registered appSphere Backend App accepts) OR TEBRA_FHIR_CLIENT_SECRET (legacy fallback, used only when no key path is set) — if set, FHIR tools are registered. Optional: TEBRA_FHIR_BASE_URL (defaults to Tebra FHIR production endpoint). src/__tests__/fhir-client-auth.test.ts pins the assertion shape and the token-request body offline; it never contacts Tebra.

Architecture

Transport: stdio via @modelcontextprotocol/sdk. The server registers tools with ListToolsRequestSchema and routes calls through a switch in CallToolRequestSchema handler.

SOAP client (src/soap-client.ts): Hand-rolled XML — no SOAP library. Builds envelopes with buildEnvelope(), sends via fetch, parses responses with regex-based extractTag/extractAllTags helpers. Retries 3x with exponential backoff (1s, 2s, 4s). Per-endpoint rate limiting tracks request counts per SOAP action and delays when approaching limits.

Read the full file on GitHub · 130 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 Changed · +96 tokens per session 46bf28415539
2mo ago First seen · 130 lines · 4,120 tokens per session scan A d9f041fac467

Subscribe to this mod's changes

tebra-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jamesrosing/tebra-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 4,216 tokens to every session, about $0.0169 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.

tebra-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tebra-mcp-server CLAUDE.mdjamesrosing/tebra-mcp-server	Instructions file	1	1mo ago	MIT	A	4,216	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

tebra-mcp-server: Instructions file for Claude Code