Skip to main content
Glama
Sign In
ArchMemory MCP

ArchMemory MCP

by IWill29
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

ArchMemory MCP

Give AI coding agents a memory of your architecture.

Open source MCP server built with Laravel that gives AI coding agents (Cursor, Claude Code, etc.) structured access to your project's architecture, rules, modules, and technical decisions.

Features (MVP)

  • 5 MCP Tools — project context, rules, modules, ADRs, change validation

  • Artisan CLI — init, analyze, update

  • .archmemory/ storage — Markdown + JSON, Git-versionable

  • Rules Engine — validates code changes against architecture rules

  • DDD Architecture — Memory, Mcp, Rules, Analysis domains

Related MCP server: projscan

Quick Start

composer install
cp .env.example .env
php artisan key:generate

# Initialize architecture memory (if not already present)
php artisan archmemory:init

# Analyze project and update architecture.md
php artisan archmemory:analyze

Cursor Integration

Add to .cursor/mcp.json (included in this repo):

{
  "mcpServers": {
    "archmemory": {
      "command": "php",
      "args": ["artisan", "mcp:start", "archmemory"],
      "cwd": "${workspaceFolder}",
      "env": {
        "ARCHMEMORY_PATH": "${workspaceFolder}/.archmemory"
      }
    }
  }
}

Then restart Cursor. The agent can call:

Tool

Description

get_project_context

Project stack, architecture, rules summary

get_architecture_rules

Full rules from rules.md

get_module_info

Module details and dependencies

get_decision_history

ADR decision records

validate_change

Check code against architecture rules

Artisan Commands

php artisan archmemory:init      # Create .archmemory/ structure
php artisan archmemory:analyze   # Generate architecture.md from project
php artisan archmemory:update    # Refresh context after changes
php artisan mcp:start archmemory # Start MCP stdio server

Project Structure

app/Domains/
├── Memory/     # Read/write .archmemory files
├── Mcp/        # MCP server + tools
├── Rules/      # Rules engine
└── Analysis/   # Project analyzer

.archmemory/    # Architecture memory (committed to Git)
docs/           # Design documents

Documentation

Testing

php artisan test          # 32 tests
vendor/bin/pint --test    # Code style check
vendor/bin/pint           # Auto-fix style

CI runs on push via GitHub Actions (.github/workflows/tests.yml).

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    This server cannot be deployed

    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Resources

    Related MCP Connectors

    Related MCP Servers

    • codeweave-mcp

      semihkayan
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.
      77 npm
      4
      Apache 2.0

    • projscan

      abhiyoheswaran1
      A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that provides AI coding agents with AST-accurate, context-budget-aware codebase querying, safety gates, and team policy integration via structured tools and a local plugin layer.
      112 npm
      4
      MIT

    • reference-mcp

      mark-burg
      A
      license
      A
      quality
      D
      maintenance
      An MCP server that helps AI agents comprehend a codebase by providing tools for navigating, searching, and understanding code structure and history.
      10
      MIT

    • lxDIG MCP

      lexCoder2
      A
      license
      B
      quality
      D
      maintenance
      MCP server that gives AI coding assistants persistent memory, structural code graph analysis, and safe multi-agent coordination, enabling them to answer architectural questions, track decisions across sessions, and coordinate safely in multi-agent workflows.
      39
      4
      MIT