Back to Browse
Free
Server data from the Official MCP Registry
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
About
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
What You'll Need
Set these up before or after installing:
PostgreSQL connection string for pgvector (default: postgresql://memwright:memwright@localhost:5432/memwright)
Environment variable: PG_CONNECTION_STRING
Neo4j database password (default: memwright)Required
Environment variable: NEO4J_PASSWORD
OpenRouter API key for embeddings (required for semantic search)Required
Environment variable: OPENROUTER_API_KEY
OpenAI API key for embeddings (alternative to OpenRouter)Required
Environment variable: OPENAI_API_KEY
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-bolnet-memwright": {
"env": {
"NEO4J_PASSWORD": "your-neo4j-password-here",
"OPENAI_API_KEY": "your-openai-api-key-here",
"OPENROUTER_API_KEY": "your-openrouter-api-key-here",
"PG_CONNECTION_STRING": "your-pg-connection-string-here"
},
"args": [
"memwright"
],
"command": "uvx"
}
}
}Security Report
10.0
Low Risk10.0Low RiskValid MCP server (2 strong, 1 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
Scanned 5 files · 1 finding
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
Reviews
No reviews yet
Be the first to review this server!