What is swag-mcp CLAUDE.md?

Project instructions for SWAG MCP, a server that lets AI assistants manage Secure Web Application Gateway reverse-proxy settings through natural-language requests. A reverse proxy receives web requests and forwards them to other services, while SWAG is the gateway being configured.

Use them when developing or testing SWAG MCP, working with its natural-language tool, nginx configuration templates, Docker deployment, or test and documentation files.

They give contributors a shared reference for the project's structure, configuration approach, testing, and development commands, reducing uncertainty when changing the codebase.

How jmagar/swag-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jmagar/swag-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/jmagar/swag-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jmagar/swag-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/jmagar/swag-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jmagar/swag-mcp/claude-md)

Your own site

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

Per session 2,366 This file is loaded in full into every session.

When invoked 2,366 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	$0.02366	$0.02366
Opus 5.5	$0.00946	$0.00946
Sonnet 5.5	$0.00473	$0.00473
Haiku 4.5	$0.00237	$0.00237

Measured 1mo ago against content hash f02e3aea8370, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swag-mcp 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 1mo 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 · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWAG MCP - Claude Memory Reference

See @README.md for complete project documentation and @.env.example for configuration options.

Project Overview

SWAG MCP is a Model Context Protocol (MCP) server that provides AI assistants with tools to manage SWAG (Secure Web Application Gateway) reverse proxy configurations through natural language commands.

Core Architecture

MCP Server Framework: FastMCP 2.11.3+ with streamable-http transport
Unified Tool Design: Single swag tool with 10 distinct actions instead of separate tools
Natural Language Interface: AI assistants translate commands to structured parameters
Docker Deployment: Production-ready containerized service
Template System: Secure Jinja2 templates for nginx config generation

Key Components

swag_mcp/: Core application package with modular architecture
tests/: Comprehensive test suite with performance, integration, and validation tests
docs/: Test command documentation with 600+ examples

Common Development Commands

Testing & Quality

# Run full test suite with coverage
uv run pytest --cov=swag_mcp --cov-report=term-missing

# Run specific test categories
uv run pytest tests/test_swag_actions.py      # Action functionality
uv run pytest tests/test_validation.py       # Input validation
uv run pytest tests/test_integration.py      # End-to-end tests

# Code quality checks
uv run ruff check swag_mcp/                  # Linting
uv run mypy swag_mcp/                       # Type checking
lefthook run pre-commit                     # Run all git hooks

Development Server

# Development mode with auto-reload
fastmcp dev swag_mcp/server.py

# Direct module execution
python -m swag_mcp

# Production Docker deployment
docker compose up -d

Build & Deploy

# Build Docker image
docker build -t swag-mcp .

# Run installer script
bash install.sh

# View container logs
docker compose logs -f swag-mcp

Tool Actions Reference

Read the full file on GitHub · 230 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.

1mo ago First seen · 230 lines · 2,366 tokens per session scan A f02e3aea8370

Subscribe to this mod's changes

swag-mcp CLAUDE.md is an instructions file published in the GitHub repository jmagar/swag-mcp (7 stars, last pushed 7d ago), licensed MIT. It adds 2,366 tokens to every session, about $0.0095 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.

LLM Memory and context Planning Python ai fastmcp mcp-server model-context-protocol

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 · 9,715 tokens

swag-mcp: Instructions file for Claude Code