What is brewfather-mcp CLAUDE.md?

Project instructions for a Brewfather MCP server, which connects coding tools to Brewfather's brewing-data service. They describe development commands and advise testing read-only API calls directly while handling data-changing calls carefully.

Use them when installing dependencies, running Python tests, checking coverage, developing MCP tools, or testing Brewfather API operations.

They explain how to work on the server and reduce the risk of accidentally changing brewing inventory, recipes, or batches during testing.

How andyonholiday/brewfather-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to andyonholiday/brewfather-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/andyonholiday/brewfather-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/andyonholiday/brewfather-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/andyonholiday/brewfather-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/andyonholiday/brewfather-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/andyonholiday/brewfather-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/andyonholiday/brewfather-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.

Your own site · 80×15

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

Per session 1,785 This file is loaded in full into every session.

When invoked 1,785 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.01785	$0.01785
Opus 5	$0.00892	$0.00892
Sonnet 5	$0.00357	$0.00357
Haiku 4.5	$0.00178	$0.00178

Measured 9d ago against content hash a8d6c66da1d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

brewfather-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl http://localhost:8000/sse` - Check if SSE endpoint is responding (will hang waiting for events, which is expected)

CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 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

This is a Model Context Protocol (MCP) server that integrates with the Brewfather API to provide brewing inventory management and recipe analysis capabilities. The server exposes tools for managing fermentables, hops, yeasts, batches, recipes, and miscellaneous brewing supplies.

The API is documented, but not well, at https://docs.brewfather.app/api In order to make robust code, we need to "test in production" by making calls to tools and debug the results. This is fine to do directly for get and list operations, but not for operations that change data. For that, we might be able to create a test entry (inventory, recipe, batch) first, then test, then clean up by carefully deleting the test item.

Development Commands

Package Management

uv run pytest - Run test suite
uv run pytest tests/test_file.py::TestClass::test_method - Run specific test
uv run pytest --cov - Run tests with coverage
uv install - Install dependencies
uv sync - Sync dependencies

MCP Development

The server supports two transport modes:

stdio (Local Development)

When using claude code, use mcpt commands to test changes to this server. The inbuilt mcp tools don't get reloaded after changes.

uv run --with mcp[cli] mcp install - Install MCP CLI tools
uv run --with 'mcp[cli]' mcp run src/main.py - Run server
uv run --with 'mcp[cli]' mcp dev src/main.py - Run server with inspector
mcpt tools uv run --with 'mcp[cli]' mcp run src/main.py - Use MCP Tools to list tools
mcpt call list_batches uv run --with 'mcp[cli]' mcp run src/main.py - Call a tool
mcpt call get_batch_detail --params '{ "batch_id": "C3hZC7P4zeNH6QJsc7FXizVGN8dkQe" }' uv run --with 'mcp[cli]' mcp run src/main.py - Call a tool with params
BREWFATHER_MCP_DEBUG=1 mcpt call get_batch_detail --params '{ "batch_id": "C3hZC7P4zeNH6QJsc7FXizVGN8dkQe" }' uv run --with 'mcp[cli]' mcp run src/main.py - Call tool with debug mode to save API calls to file
alias -g BF="uv run --with 'mcp[cli]' mcp run src/main.py" - Alias to use with mcpt, eg mcpt tools BF

Read the full file on GitHub · 146 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 · 146 lines · 1,785 tokens per session scan A a8d6c66da1d2

Subscribe to this mod's changes

brewfather-mcp CLAUDE.md is an instructions file published in the GitHub repository andyonholiday/brewfather-mcp (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,785 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

brewfather-mcp: Instructions file for Claude Code