Borrowing it
Nothing to install: this file belongs to prashant-cr/Clinic-front-desk-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.
curl -O https://raw.githubusercontent.com/prashant-cr/Clinic-front-desk-MCP-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/prashant-cr/Clinic-front-desk-MCP-serverWrote 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.
[](https://agentmods.dev/instructions/prashant-cr/clinic-front-desk-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/prashant-cr/clinic-front-desk-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/prashant-cr/clinic-front-desk-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.
<a href="https://agentmods.dev/instructions/prashant-cr/clinic-front-desk-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/prashant-cr/clinic-front-desk-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02018 | $0.02018 |
| Opus 5 | $0.01009 | $0.01009 |
| Sonnet 5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
Clinic-front-desk-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Clinic Front-Desk MCP Server
Project Overview
Build clinic-frontdesk-mcp: an open-source MCP (Model Context Protocol) server that turns any MCP-compatible client (Claude Desktop, Claude Code, custom agents) into an AI receptionist for a small medical clinic.
The server exposes tools for appointment booking, rescheduling, reminders, patient intake, and clinic FAQs. The LLM client is the "brain"; this server provides the hands.
License: MIT. Language: Python 3.11+. MCP SDK: official mcp Python SDK (use FastMCP). Storage: SQLite (zero-config, file-based). Distribution: installable via uvx / pip, runnable over stdio transport.
Design Principles
- Human-in-the-loop for all writes. Tools that book, cancel, or message must return a clear confirmation summary. Destructive actions (cancel, delete) require an explicit
confirm=trueparameter — if called without it, return a preview of what would happen and ask for confirmation. - No clinical advice. This server handles logistics only. If tools receive medical questions, the FAQ tool should return a canned "please discuss with the doctor" style entry. Never store or return diagnostic recommendations.
- Privacy-first. All data stays in a local SQLite file. No external calls in v1 except optional notification adapters (stubbed by default). Never log patient names/phones to stdout (stdout is the MCP transport anyway — log to stderr or a file, and redact PII in logs).
- Zero-config startup. First run auto-creates the database with schema + seed data. Config via environment variables with sensible defaults.
- Timezone-aware. Clinic timezone from config (default
Asia/Kolkata). All stored timestamps in UTC ISO 8601; all tool inputs/outputs in clinic-local time.
Repository Structure
clinic-frontdesk-mcp/
├── CLAUDE.md
├── README.md # install, Claude Desktop config snippet, demo script
├── LICENSE # MIT
├── pyproject.toml # project metadata, deps, entry point: clinic-frontdesk-mcp
├── src/
│ └── clinic_frontdesk_mcp/
│ ├── __init__.py
│ ├── server.py # FastMCP app: tool definitions ONLY (thin layer)
│ ├── db.py # SQLite connection, schema creation, migrations
│ ├── models.py # dataclasses / pydantic models
│ ├── scheduling.py # availability logic, slot math, conflict checks
│ ├── patients.py # patient CRUD + intake logic
│ ├── faq.py # FAQ lookup (simple keyword + fuzzy match)
│ ├── notifications.py# adapter interface + ConsoleAdapter (stub) + TwilioAdapter (optional)
│ └── config.py # env-var config loading
├── seed/
│ └── seed_data.sql # demo clinic, doctors, FAQ entries, sample patients
├── tests/
│ ├── test_scheduling.py
│ ├── test_tools.py # tool-level integration tests via FastMCP test client
│ └── test_db.py
└── .github/
└── workflows/ci.yml # ruff + pytest on push
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.
- 10d ago First seen · 125 lines · 2,018 tokens per session scan A 80cb0b058ff1
Clinic-front-desk-MCP-server CLAUDE.md is an instructions file published in the GitHub repository prashant-cr/Clinic-front-desk-MCP-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,018 tokens to every session, about $0.0101 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.
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.