What is charm-mcp-server CLAUDE.md?

Project instructions for CharmHealth's charm-mcp-server, a Python server that provides tools through the Model Context Protocol, a standard way for applications to expose tools to AI agents.

They are for building and running the server, understanding its tool-domain structure, working with Jira tickets, and following the project's Python and monitoring setup.

They give an agent the project's expected commands, Git settings, issue-tracking details, architecture, and technology requirements.

How CharmHealth/charm-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CharmHealth/charm-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/CharmHealth/charm-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/CharmHealth/charm-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/charmhealth/charm-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/charmhealth/charm-mcp-server/claude-md)

Your own site

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

Per session 4,730 This file is loaded in full into every session.

When invoked 4,730 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	$0.04730	$0.04730
Opus 5	$0.02365	$0.02365
Sonnet 5	$0.00946	$0.00946
Haiku 4.5	$0.00473	$0.00473

Measured 9d ago against content hash b18f5b5d6d91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

charm-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 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

charm-mcp-server — Project Instructions

Build & Run

Entry point: src/mcp_server.py — composite FastMCP server mounting one sub-server per tool domain.
Environment: Python 3.13+, managed via uv.

Git Workflow

Main branch: main
Remote: origin → https://github.com/CharmHealth/charm-mcp-server.git

Jira

Project key: CH
Atlassian cloudId: 75ce53d2-c120-470e-b740-876c721a8960 (site: charmhealthtech.atlassian.net)
Default assignee: Sumana Ramanathan
Source of truth for the July sprint: chai-action-plan-sept2026.md (lives in Google Drive / referenced from cortex's docs, not in this repo) — tickets like CH-688 (J6) are generated from sections of that plan.

Architecture Overview

Tech Stack

Python 3.13, FastMCP (MCP server framework), httpx for outbound HTTP, OpenTelemetry + Prometheus for telemetry, python-dotenv for local env config.

Composite server pattern

src/mcp_server.py builds one mcp_composite_server = FastMCP(...) and mounts one sub-server per tool-domain file:

mcp_composite_server.mount(server=core_tools_mcp)
mcp_composite_server.mount(server=patient_management_mcp)
mcp_composite_server.mount(server=scheduling_tools_mcp)
mcp_composite_server.mount(server=encounter_management_mcp)
mcp_composite_server.mount(server=clinical_data_mcp)
mcp_composite_server.mount(server=clinical_support_mcp)
mcp_composite_server.mount(server=task_management_mcp)
mcp_composite_server.mount(server=communication_mcp)
mcp_composite_server.mount(server=billing_mcp)
mcp_composite_server.mount(server=intake_forms_mcp)

New tool domains follow this exact pattern: one new file in src/tools/, its own <domain>_mcp = FastMCP(name="..."), mounted with one added line here — and imported + added to __all__ in src/tools/__init__.py. mcp_server.py pulls everything via from tools import *, so mounting alone isn't enough if the sub-server isn't also exported from tools/__init__.py — easy to miss, caught this exact gap when adding billing_mcp.

Read the full file on GitHub · 87 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.

9d ago First seen · 87 lines · 4,730 tokens per session scan A b18f5b5d6d91

Subscribe to this mod's changes

charm-mcp-server CLAUDE.md is an instructions file published in the GitHub repository CharmHealth/charm-mcp-server (11 stars, last pushed yesterday), licensed MIT. It adds 4,730 tokens to every session, about $0.0236 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.

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

charm-mcp-server: Instructions file for Claude Code