mcp-memory-keeper

🥈Silver

MCP Memory Keeper is a server for managing persistent context in AI coding assistants. It helps developers maintain context across sessions, improving efficiency and accuracy. Integrates with Claude AI and uses SQLite for data storage.

114180Updated Today

Intermediate30min to implementautomation

Saves ~180 min per use

Quick InstallView Source

git clone https://github.com/mkreyman/mcp-memory-keeper.git

Works with:

Claude

Overview

About This Skill

How to Use

["Install and configure the MCP Memory Keeper server. Ensure it’s running locally or accessible via your AI assistant’s MCP client.","Load the context for your project by referencing the relevant files or modules. For example, use `Retrieve context for [FILE_PATH]` in your prompt.","Review the retrieved context to understand past decisions, dependencies, or unresolved issues. Ask the AI to summarize key points if the context is verbose.","Use the context to guide your current task. For example, ask the AI to suggest improvements, debug issues, or generate documentation based on the stored decisions.","Store the updated context after making changes. Include a concise note summarizing the changes or next steps. For example: `Store this context with the note: 'Fixed bug in token validation and added logging.'`"]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/mkreyman/mcp-memory-keeper

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use the MCP Memory Keeper to [ACTION] for [PROJECT/CODEBASE]. Retrieve the context for [SPECIFIC_FILE_OR_MODULE] and summarize the key decisions made in [RECENT_SESSION]. Then, suggest improvements based on [GOAL, e.g., performance optimization, bug fixes]. Finally, store the updated context with a note: '[SUMMARY_OF_CHANGES]'.

Example Output

For the open-source project **FastAPI-User-Auth**, I used the MCP Memory Keeper to retrieve the context for `auth_service.py` and the recent session where we migrated from JWT to OAuth2. The stored context showed that the team decided to use `authlib` for OAuth2 integration due to its better compatibility with FastAPI’s dependency injection system. Key decisions included:

1. **Token Storage**: Switched from Redis to PostgreSQL for token persistence to simplify infrastructure.
2. **Rate Limiting**: Implemented `slowapi` for OAuth2 token requests to prevent abuse.
3. **Error Handling**: Added custom exceptions for OAuth2-specific errors (e.g., `InvalidTokenError`).

Based on these decisions, I suggested:
- **Performance Optimization**: Replace PostgreSQL with `SQLite` for token storage in development environments to reduce latency.
- **Security Enhancement**: Add `refresh_token` rotation to mitigate replay attacks.
- **Testing**: Write integration tests for the OAuth2 flow using `pytest` and `httpx`.

The updated context was stored with the note: *'Optimized token storage for dev, added refresh token rotation, and outlined testing strategy.'*

**Stored Context Summary**:
```json
{
"file": "auth_service.py",
"last_updated": "2024-05-20",
"key_decisions": ["Migrated from JWT to OAuth2", "Used authlib for OAuth2", "Switched to PostgreSQL for token storage"],
"suggested_improvements": ["Use SQLite for dev token storage", "Add refresh token rotation", "Write integration tests"],
"notes": "Optimized token storage for dev, added refresh token rotation, and outlined testing strategy."
}
```