What is mcp-server-architect CLAUDE.md?

A set of development instructions for architect-mcp, an MCP server project. It describes setup, building, linting, publishing, and integration testing.

Use it to install the project, run Ruff and pytest, record integration-test responses, build packages, and publish new versions.

It gives contributors a shared process for checking and releasing changes, including tests that use recorded real API responses instead of mocks.

How funtusov/mcp-server-architect configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to funtusov/mcp-server-architect. 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/funtusov/mcp-server-architect/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/funtusov/mcp-server-architect

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

Your own site

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

Per session 848 This file is loaded in full into every session.

When invoked 848 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	$0.00848	$0.00848
Opus 5.5	$0.00339	$0.00339
Sonnet 5.5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash 28f3ba26cb30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-architect 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Guidelines for architect-mcp

Commands

Setup: uv add -e . (install in dev mode)
Dependencies: uv add google-genai python-dotenv (required packages)
Build: uv build --no-sources
Run: uvx mcp-server-architect
Lint: ruff check .
Format: ruff format .
Fix lint issues: ruff check --fix .

Publishing a New Version

For a complete guide on building, testing, and publishing new versions, see PUBLISH.md for detailed step-by-step instructions.

Testing

Run the pytest integration tests when developing and before publishing
For normal development, use linting to check code quality: ruff check .

Integration Tests Best Practices

Use pytest-recording for integration tests to record live API responses
Never use mocks in integration tests; they create brittle tests that don't catch real issues
Run tests with recorded cassettes:
```
uv run pytest tests/ -v
```
To rewrite all cassettes:
```
uv run pytest tests/ --record-mode=all
```
Remember to check cassettes into source control but filter sensitive data

Committing Changes

When committing changes:

Use a succinct one-line commit message
Don't include "Generated with Claude Code" or "Co-Authored-By" lines
Run linter checks before committing
Always add all modified files including lock files for a clean state (git add .)
If certain files should not be committed, explicitly gitignore them

UV Cheatsheet

Add dependency: uv add <package> or uv add <package> --dev
Remove dependency: uv remove <package> or uv remove <package> --dev
Run in venv: uv run <command> (e.g. uv run pytest)
Sync environment: uv sync
Update lockfile: uv lock
Install tool: uv tool install <tool> (e.g. uv tool install ruff)

Code Style

Line length: 120 characters (configured in pyproject.toml)
Python 3.10+ compatible
Document functions with docstrings (triple quotes)
File structure: shebang line, docstring, imports, constants, classes/functions
Imports: standard library first, then third-party, then local modules
Error handling: use try/except blocks with specific exceptions and logging
Naming: snake_case for variables/functions, PascalCase for classes
Logging: use the module-level logger defined at the top of each file

Read the full file on GitHub · 83 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 First seen · 83 lines · 848 tokens per session scan A 28f3ba26cb30

Subscribe to this mod's changes

mcp-server-architect CLAUDE.md is an instructions file published in the GitHub repository funtusov/mcp-server-architect (5 stars, last pushed 1y ago), licensed MIT. It adds 848 tokens to every session, about $0.0034 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.

Building agents

mcp-server-architect CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server-architect CLAUDE.mdfuntusov/mcp-server-architect	Instructions file	5	1y ago	MIT	A	848	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-server-architect: Instructions file for Claude Code