Skip to main content
Glama

MCP Standards - Personal Memory for Claude

⚠️ ARCHIVED PROJECT: This repository is archived and provided for reference only. The project was experimental and served as a proof-of-concept for automatic preference learning with AgentDB vector memory. See ARCHIVE.md for complete details.

Make Claude remember YOUR preferences automatically. Zero config, zero manual steps.

MIT License Python 3.10+ Archived


🎯 What This Does

Stop repeating yourself to Claude. This MCP server learns your preferences automatically:

You: "Install pytest"
Claude: pip install pytest

You: "Actually, use uv not pip"
Claude: βœ“ Remembered

Next session:
You: "Install requests"
Claude: uv pip install requests  [automatic]

One correction. Forever remembered.


⚑ Quick Start (5 Minutes)

1. Install

git clone https://github.com/airmcp-com/mcp-standards.git
cd mcp-standards

# Install dependencies
npm install

# Setup AgentDB
npm run setup

2. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-standards": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/ABSOLUTE/PATH/TO/mcp-standards",
        "python",
        "-m",
        "mcp_standards.server_simple"
      ]
    }
  }
}

⚠️ Replace /ABSOLUTE/PATH/TO/ with your actual path!

3. Restart Claude Desktop

Quit and relaunch Claude Desktop.

4. Test It!

You: "Remember: use uv not pip"
Claude: βœ“ Remembered: 'use uv not pip' (python)

You: "What do you remember?"
Claude: I remember you prefer:
- Use uv not pip for Python projects

That's it! You're done. πŸŽ‰


🧠 How It Works

Automatic Learning

Just correct Claude naturally - it learns automatically:

Session 1:
You: "Use uv not pip"
β†’ Auto-detected and stored in AgentDB

Session 2+:
You: "Install anything"
β†’ Claude uses uv automatically

What Gets Remembered

βœ… Tool preferences: "use uv not pip", "prefer yarn over npm" βœ… Workflow patterns: "run tests before commit" βœ… Code style: "use TypeScript for new files" βœ… Project conventions: "follow PEP 8"

Categories (Auto-Detected)

  • python - Python/pip/uv preferences

  • javascript - npm/yarn/pnpm preferences

  • git - Git workflow preferences

  • docker - Docker/container preferences

  • testing - Test framework preferences

  • general - Everything else


πŸ“Š Features

Feature

Status

Auto-detection

βœ… Detects "use X not Y" automatically

Semantic search

βœ… <1ms with AgentDB (150x faster than SQLite)

Cross-session

βœ… Preferences persist forever

Zero config

βœ… Works out of the box

100% local

βœ… No cloud, all private

Simple

βœ… 5-minute setup


πŸ“– Documentation


πŸ› οΈ MCP Tools Available

Personal Memory (Simple Version)

// Store preference
remember({
    content: "use uv not pip",
    category: "python"
})

// Search preferences
recall({
    query: "package manager",
    top_k: 5
})

// List all categories
list_categories()

// Get statistics
memory_stats()

Config Standards (Bonus)

// Generate minimal CLAUDE.md from project config files
generate_ai_standards({
    project_path: ".",
    formats: ["claude"]
})

πŸš€ Architecture

Simple & Fast

User corrects Claude
   ↓
Auto-detection hook triggers
   ↓
Stores in AgentDB (semantic vector memory)
   ↓
Next session: Claude queries AgentDB automatically
   ↓
Uses remembered preference

Technologies

  • AgentDB - Ultra-fast vector memory (<1ms search)

  • Python - MCP server (async)

  • SQLite - Fallback storage

  • MCP Protocol - Claude Desktop integration

  • 100% Local - No cloud dependencies


πŸ“ Project Structure

mcp-standards/
β”œβ”€β”€ src/mcp_standards/
β”‚   β”œβ”€β”€ agentdb_client.py        # AgentDB wrapper
β”‚   β”œβ”€β”€ hooks/auto_memory.py     # Auto-detection
β”‚   └── server_simple.py         # Simple MCP server
β”œβ”€β”€ tests/
β”‚   └── test_simple_setup.py     # Validation tests
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ QUICKSTART_SIMPLE.md     # Setup guide
β”‚   β”œβ”€β”€ VALIDATION_CHECKLIST.md  # Testing guide
β”‚   └── SIMPLE_V2_PLAN.md        # Technical details
β”œβ”€β”€ scripts/
β”‚   └── setup-agentdb.js         # Setup script
β”œβ”€β”€ .claude/skills/
β”‚   └── remember-preferences.md  # Claude skill
└── README.md                     # This file

Clean. Simple. Works.


πŸ§ͺ Testing

Run automated validation:

python3 tests/test_simple_setup.py

Expected output:

βœ“ PASS: Directory Structure
βœ“ PASS: Required Files
βœ“ PASS: Module Imports
βœ“ PASS: AgentDB Client Init
βœ“ PASS: Auto Memory Patterns

Results: 5/5 tests passed
Status: Ready for dev testing πŸš€

πŸ› Troubleshooting

Setup fails

# Check Node.js version
node --version  # Need v18+

# Install AgentDB manually
npm install -g agentdb
npx agentdb --version

Claude Desktop doesn't connect

# Check logs
tail -f ~/Library/Logs/Claude/mcp*.log

# Look for initialization messages
# Should see: "MCP Standards (Simple) initialized"

Preferences not remembered

Check that:

  1. Server is running (check Claude Desktop MCP status)

  2. Corrections use clear phrases ("use X not Y")

  3. AgentDB path exists: ~/.mcp-standards/agentdb

More help: See Validation Checklist


🎯 Performance

Metric

Value

Setup time

<5 minutes

Server startup

<2 seconds

Search speed

<1ms (AgentDB HNSW)

Detection

Real-time (async)

Storage

<10ms

Memory usage

~50MB (embedding model)

150x faster than SQLite. Zero lag.


πŸ”’ Privacy

  • βœ… 100% local - Everything stored in ~/.mcp-standards/

  • βœ… No cloud - No external API calls

  • βœ… No telemetry - No data collection

  • βœ… Your data - You control everything


πŸ“ What Changed (v2 Simple)

We removed all the complexity:

v1 (Old)

v2 Simple (New)

Manual MCP calls (4-5 steps)

βœ… Automatic (zero steps)

SQLite keyword search (50ms+)

βœ… AgentDB vector search (<1ms)

No semantic matching

βœ… Semantic understanding

Complex setup

βœ… 5-minute setup

6,000+ LOC

βœ… ~950 LOC

Result: 80% less code, 100x better UX


🀝 Contributing

This is a personal side project. If you want to contribute:

  1. Try it yourself first

  2. Open an issue describing what you want to add

  3. Wait for feedback before writing code

Please don't: Submit large PRs without discussion first.


πŸ“œ License

MIT License - See LICENSE file


πŸ™ Credits

Built with inspiration from:


πŸ’¬ Questions?

Q: Why not just use v1? A: v1 requires 4-5 manual MCP calls per correction. v2 is zero-touch.

Q: Do I need AgentDB? A: Yes, but it's installed automatically via npm run setup.

Q: Is my data private? A: 100% local. Everything stored in ~/.mcp-standards/. No cloud.

Q: What if I want the old version? A: Use src/mcp_standards/server.py instead of server_simple.py.


πŸš€ Next Steps

# Try it now
git clone https://github.com/airmcp-com/mcp-standards.git
cd mcp-standards
npm run setup

# See: docs/QUICKSTART_SIMPLE.md

Stop repeating yourself. Start remembering automatically. 🎯


πŸ“¦ Archive Status

This project is archived. See ARCHIVE.md for:

  • Complete project status and achievements

  • Security audit results

  • Full documentation index

  • Lessons learned and technical insights

  • How to use this repository as reference


Made with ❀️ by keeping it simple

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/airmcp-com/mcp-standards'

If you have feedback or need assistance with the MCP directory API, please join our Discord server