Personal Brain MCP
Provides a PostgreSQL-backed long-term personal memory system, enabling storage, retrieval, and querying of personal context and memories using SQL and custom MCP tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Personal Brain MCPsave a note about my meeting with Sarah yesterday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Personal Brain MCP v0.2
A PostgreSQL-backed long-term personal-memory MCP server. It supports local Docker PostgreSQL and remote Neon PostgreSQL, and exposes a Streamable HTTP MCP endpoint for hosting on Render.
MCP tools
get_personal_contextsave_memoryquery_personal_database— model-generated read-only SQL onlyupdate_context_manifest
Related MCP server: hippocampus-mcp
Remote endpoints
MCP:
POST /mcp(Streamable HTTP)Health check:
GET /health
Local development with Docker PostgreSQL
cp .env.example .env
# Remove/comment DATABASE_URL in .env to use the local Docker settings.
docker compose up -d
npm install
npm run check
npm run devThe server listens on http://localhost:10000 by default.
Neon / Render
Set these environment variables in Render:
DATABASE_URL=<Neon connection string>
MCP_API_KEY=<long random secret, recommended>
USER_ID=main
USER_NAME=<your display name>
USER_LANGUAGE=ko
USER_TIMEZONE=Asia/SeoulRender supplies PORT automatically. The app binds to 0.0.0.0:$PORT.
Build command:
npm install && npm run buildStart command:
npm startHealth check path:
/healthAfter deployment, the MCP endpoint is:
https://<your-render-service>.onrender.com/mcpIf MCP_API_KEY is set, clients must send:
Authorization: Bearer <MCP_API_KEY>Database initialization
On startup, the app safely creates the required tables and indexes if they do not already exist. pgvector is optional in v0.2; failure to enable it does not prevent startup.
Security
.envis ignored by Git.Never commit Neon connection strings, passwords, API keys, or tokens.
query_personal_databaseaccepts only oneSELECT/WITHquery, runs it in a read-only transaction, and caps output at 100 rows.
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides persistent semantic memory backed by PostgreSQL and pgvector for storing and searching thoughts via vector embeddings. It enables dimensional organization, conflict detection, and historical tracking of facts, decisions, and observations.14 npmAGPL 3.0
- AlicenseAqualityBmaintenanceA personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.6MIT
- FlicenseNot gradedqualityDmaintenanceA personal memory MCP server that stores and retrieves conversation memories, enabling AI agents to recall past discussions, promises, and preferences using natural language.-
- AlicenseNot gradedqualityBmaintenanceA self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.3 npmMIT