# Engram MCP server

> Provides a self-hostable AI memory layer that retrieves user memories from pgvector and injects them into LLM chat prompts.

- Repository: https://github.com/macayu17/Engram
- Page: https://hostedmcp.org/servers/macayu17/engram
- Transport: —
- Stars: 4
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `CLERK_SECRET_KEY` | no | no |  |
| `DATABASE_MAX_POOL_SIZE` | no | no |  |
| `DATABASE_MIN_POOL_SIZE` | no | no |  |
| `DATABASE_STATEMENT_CACHE_SIZE` | no | no |  |
| `DATABASE_URL` | no | no |  |
| `ENGRAM_API_KEY` | no | no |  |
| `ENGRAM_PROVIDER_KEY_ENCRYPTION_KEY` | no | no |  |
| `ENGRAM_SERVICE_KEY` | no | no |  |
| `EXTRACTION_PROVIDER` | no | no |  |
| `MCP_SERVICE_KEY` | no | no |  |
| `NEXT_PUBLIC_API_URL` | no | no |  |
| `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` | no | no |  |
| `OPENAI_API_KEY` | no | no |  |
| `POSTGRES_PASSWORD` | no | no |  |

## FAQ

### What is Engram?

Engram is a self-hostable AI memory layer that sits between an application and an LLM provider to manage user memories using pgvector.

### Can I use Supabase with Engram?

Yes, Engram can use Supabase as its PostgreSQL and pgvector database.

### How are memories reviewed and managed?

The product dashboard allows users to separate pending, approved, and rejected memories, perform bulk reviews, and compare proposed changes against approved facts.

### Does Engram support different LLM providers?

Yes, it can forward requests to OpenAI, Gemini, Ollama, or Anthropic.
