Skip to main content
Glama

MCP Standards - Personal Memory for Claude

โš ๏ธ 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


๐ŸŽฏ 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: โœ“ Remembered Next session: You: "Install requests" Claude: uv pip install requests [automatic]

One correction. Forever remembered.


โšก 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" ] } } }

โš ๏ธ Replace

3. Restart Claude Desktop

Quit and relaunch Claude Desktop.

4. Test It!

You: "Remember: use uv not pip" Claude: โœ“ 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. ๐ŸŽ‰


๐Ÿง  How It Works

Automatic Learning

Just correct Claude naturally - it learns automatically:

Session 1: You: "Use uv not pip" โ†’ Auto-detected and stored in AgentDB Session 2+: You: "Install anything" โ†’ Claude uses uv automatically

What Gets Remembered

โœ… Tool preferences: "use uv not pip", "prefer yarn over npm" โœ… Workflow patterns: "run tests before commit" โœ… Code style: "use TypeScript for new files" โœ… 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


๐Ÿ“Š Features

Feature

Status

Auto-detection

โœ… Detects "use X not Y" automatically

Semantic search

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

Cross-session

โœ… Preferences persist forever

Zero config

โœ… Works out of the box

100% local

โœ… No cloud, all private

Simple

โœ… 5-minute setup


๐Ÿ“– Documentation


๐Ÿ› ๏ธ 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"] })

๐Ÿš€ Architecture

Simple & Fast

User corrects Claude โ†“ Auto-detection hook triggers โ†“ Stores in AgentDB (semantic vector memory) โ†“ Next session: Claude queries AgentDB automatically โ†“ 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


๐Ÿ“ Project Structure

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

Clean. Simple. Works.


๐Ÿงช Testing

Run automated validation:

python3 tests/test_simple_setup.py

Expected output:

โœ“ PASS: Directory Structure โœ“ PASS: Required Files โœ“ PASS: Module Imports โœ“ PASS: AgentDB Client Init โœ“ PASS: Auto Memory Patterns Results: 5/5 tests passed Status: Ready for dev testing ๐Ÿš€

๐Ÿ› 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


๐ŸŽฏ 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.


๐Ÿ”’ Privacy

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

  • โœ… No cloud - No external API calls

  • โœ… No telemetry - No data collection

  • โœ… Your data - You control everything


๐Ÿ“ What Changed (v2 Simple)

We removed all the complexity:

v1 (Old)

v2 Simple (New)

Manual MCP calls (4-5 steps)

โœ… Automatic (zero steps)

SQLite keyword search (50ms+)

โœ… AgentDB vector search (<1ms)

No semantic matching

โœ… Semantic understanding

Complex setup

โœ… 5-minute setup

6,000+ LOC

โœ… ~950 LOC

Result: 80% less code, 100x better UX


๐Ÿค 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.


๐Ÿ“œ License

MIT License - See LICENSE file


๐Ÿ™ Credits

Built with inspiration from:


๐Ÿ’ฌ 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.


๐Ÿš€ 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. ๐ŸŽฏ


๐Ÿ“ฆ 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 โค๏ธ by keeping it simple

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