Atlas / MCP servers / codenamev / AI Software Architect

AI Software ArchitectSAFE

Name: AI Software Architect
Author: codenamev

mcp/codenamev/ai-software-architect

MCP server by codenamev · adr · architectural decision records · architecture · Audited 2026-10-07

AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode. Now available as Claude Code Plugin for easiest installation.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

6 3r · 3w · 0d

Transport

stdio

License

—

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A markdown-based framework for implementing rigorous software architecture practices in any project, with specialized AI assistant integration.

Introducing AI Software Architect 🚀 - Watch Video

Overview

This framework provides a structured approach to:

Architecture Documentation - Templates and processes for documenting architectural decisions
Architecture Reviews - A multi-perspective review process with specialized reviewers
Architecture Recalibration - Process for translating reviews into concrete implementation plans
Progress Tracking - Tools for monitoring the implementation of architectural changes
AI Integration - Seamless collaboration with AI coding assistants

For detailed usage instructions, see USAGE.md. For troubleshooting and advanced usage, see TROUBLESHOOTING.md.

Installation

Choose the installation method for your AI assistant:

Claude Code Installation

Claude Code supports three installation methods:

Option 1: Claude Code Plugin (Recommended) 🆕

Install via the Claude Code plugin system with automatic updates:

# In Claude Code, run these commands:
/plugin marketplace add codenamev/ai-software-architect
/plugin install ai-software-architect@ai-software-architect

That's it! The framework is now available in all your projects — including the seven skills, MCP server, and generated subagents as a single unit.

See USAGE-WITH-CLAUDE-PLUGIN.md for detailed installation guide, troubleshooting, and comparison with other methods.

Benefits: Simplest installation, automati

Read from source at commit 2be21bd5acc8OBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add architecture-tools -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "architecture-tools": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}

Exposed tools (6)

3 read · 3 write · 0 destructive.

Tool	Risk	Description
`configure_pragmatic_mode`	write	Enable and configure Pragmatic Mode (YAGNI Enforcement) to prevent over-engineering
`create_adr`	write	Create an Architectural Decision Record (ADR)
`get_architecture_status`	read	Get the current status of architecture documentation and decisions
`get_implementation_guidance`	read	Get implementation methodology, influences, and practices configuration for
`list_architecture_members`	read	List all available architecture team members and their specialties
`setup_architecture`	write	Set up the AI Software Architect framework in the current project

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: none-observed
Network: none-observed
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (13)

LOWInventory / provenance · inv.no_license · CWE-1104

Why it matters. no LICENSE file and no repo licence

Fix. add a licence

LOWInventory / provenance · inv.symlink · CWE-1104

.coding-assistants/claude-code/claude-code.md

.coding-assistants/claude-code/claude-code.md

Why it matters. link not followed

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

.github/workflows/codex-tests.yml:56

cp -r ../../.architecture ./.architecture

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

.github/workflows/codex-tests.yml:57

cp -r ../../.coding-assistants ./.coding-assistants

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tools/test/setup-fidelity.test.js:8

import { ArchitectureServer } from '../../mcp/index.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tools/test/subagent-generator.test.js:30

const result = generateSubagent({ ...SAMPLE_MEMBER, id: '../../.claude/hooks/evil' });

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

mcp/package.json

@modelcontextprotocol/sdk, yaml, fs-extra, @types/node

Why it matters. 4 dependency range(s) float

Fix. pin exact versions or ship a lockfile

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

tools/package.json

yaml

Why it matters. 1 dependency range(s) float

Fix. pin exact versions or ship a lockfile