A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
Enhanced MCP memory server with SQLite backend for improved performance and scalability
An enhanced fork of the official MCP Memory Server with SQLite backend support for improved performance and scalability. Now at v1.0.0 - Production Ready! 🚀
<<<<<<< HEAD Based on benchmarks with 10,000 entities:
| Operation | JSON Backend | SQLite Backend | Improvement |
|---|---|---|---|
| Entity Creation | 678ms | 145ms | 4.7x faster |
| Search (5 queries) | 90ms | 67ms | 1.3x faster |
| Memory Usage | 11.3MB | 11.3MB | Similar |
| Storage Size | 3.9MB | 9.6MB | JSON more compact |
Based on comprehensive benchmarks with datasets from 10K to 500K entities (validated 2025-08-08):
| Operation | JSON Backend | SQLite Backend | Improvement |
|---|---|---|---|
| Entity Creation (100K) | 60.86s | 1.95s | 31x faster |
| Entity Creation (500K) | 979.38s | 8.24s | 119x faster |
| Search (10K dataset) | 312.91ms/search | 13.41ms/search | 23x faster |
| Memory Usage | ~400MB (100K) | ~20MB (100K) | 92% less |
| Storage Size* | TBD | TBD | ~30% smaller |
*Storage size validation pending; preliminary tests show 30-40% reduction
Note: Performance improvements scale with dataset size. Larger datasets show more dramatic improvements, with 500K entities showing 119x faster creation and consistent 90%+ memory reduction. Benchmarks run on standard hardware with Node.js v22.
dev/v1.0.2
docker run -d \
--name mcp-memory-enhanced \
-p 6970:6970 \
-v /path/to/data:/data \
-e STORAGE_TYPE=sqlite \
ghcr.io/jamesprial/mcp-memory-enhanced:latest
# Latest version
npm install github:JamesPrial/mcp-memory-enhanced
# Specific version
npm install github:JamesPrial/mcp-memory-enhanced#v1.0.0
git clone https://github.com/JamesPrial/mcp-memory-enhanced.git
cd mcp-memory-enhanced
npm install
npm run build
docker-compose up -d
| Variable | Default | Description |
|---|---|---|
STORAGE_TYPE | json | Storage backend: sqlite or json |
STORAGE_PATH | OS temp dir | Directory for data files |
SQLITE_DB_NAME | knowledge.db | SQLite database filename |
PORT | 6970 | Health check server port (Docker only) |
LOG_LEVEL | info | Logging level |
Add to your MCP client settings:
{
"mcpServers": {
"memory": {
"command": "node",
"args": ["/path/to/mcp-memory-enhanced/dist/index.js"],
"env": {
"STORAGE_TYPE": "sqlite",
"STORAGE_PATH": "/path/to/data"
}
}
}
}
# Using the migration tool
npm run migrate /path/to/knowledge-graph.jsonl
Or with Docker:
docker run --rm \
-v /path/to/json-data:/source \
-v /path/to/sqlite-data:/data \
ghcr.io/jamesprial/mcp-memory-enhanced:latest \
node dist/migrate.js /source/knowledge-graph.jsonl
The Docker container provides a health endpoint at http://localhost:6970/health:
{
"status": "healthy",
"timestamp": "2025-08-05T12:00:00.000Z",
"storage": {
"type": "sqlite",
"stats": {
"entityCount": 1000,
"relationCount": 500,
"observationCount": 2000,
"storageSize": 1048576
}
}
}
npm test
docker build -f Dockerfile.standalone -t mcp-memory-enhanced .
STORAGE_TYPE=sqlite npm start
The Enhanced MCP Memory Server uses a clean storage abstraction layer:
┌─────────────────┐
│ MCP Client │
└────────┬────────┘
│ stdio
┌────────▼────────┐
│ MCP Server │
│ (index.ts) │
└────────┬────────┘
│
┌────────▼────────┐
│ KnowledgeGraph │
│ Manager │
└────────┬────────┘
│
┌────────▼────────┐
│ IStorageBackend │
└────────┬────────┘
│
┌────┴────┐
│ │
┌───▼───┐ ┌──▼────┐
│ JSON │ │SQLite │
└───────┘ └───────┘
Contributions are welcome! Please:
git checkout -b feat/amazing-feature)git commit -m 'feat: add amazing feature')git push origin feat/amazing-feature)This project is licensed under the MIT License - see the LICENSE file for details.
🤖 Enhanced for production use with ❤️ by @JamesPrial
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots
MCP server integration for DaVinci Resolve Studio
A Jetbrains IDE IntelliJ plugin aimed to provide coding agents the ability to leverage intelliJ's indexing of the codeba